musicdsp/audio-algo-speex
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Compare commits

base: musicdsp:main
Branches Tags
musicdsp:main
musicdsp:dev
musicdsp:v1.0.0
musicdsp:0.2.0
musicdsp:0.1.1
musicdsp:0.1.0
..
compare: musicdsp:0.1.1
Branches Tags
musicdsp:dev
musicdsp:main
musicdsp:v1.0.0
musicdsp:0.2.0
musicdsp:0.1.1
musicdsp:0.1.0

No commits in common. "main" and "0.1.1" have entirely different histories.
main ... 0.1.1

14 changed files with 110 additions and 1136 deletions
Show Stats Expand all files Collapse all files

373
LICENSE
View File

@ -1,373 +0,0 @@
Mozilla Public License Version 2.0
==================================
1. Definitions
--------------
1.1. "Contributor"
means each individual or legal entity that creates, contributes to
the creation of, or owns Covered Software.
1.2. "Contributor Version"
means the combination of the Contributions of others (if any) used
by a Contributor and that particular Contributor's Contribution.
1.3. "Contribution"
means Covered Software of a particular Contributor.
1.4. "Covered Software"
means Source Code Form to which the initial Contributor has attached
the notice in Exhibit A, the Executable Form of such Source Code
Form, and Modifications of such Source Code Form, in each case
including portions thereof.
1.5. "Incompatible With Secondary Licenses"
means
(a) that the initial Contributor has attached the notice described
in Exhibit B to the Covered Software; or
(b) that the Covered Software was made available under the terms of
version 1.1 or earlier of the License, but not also under the
terms of a Secondary License.
1.6. "Executable Form"
means any form of the work other than Source Code Form.
1.7. "Larger Work"
means a work that combines Covered Software with other material, in
a separate file or files, that is not Covered Software.
1.8. "License"
means this document.
1.9. "Licensable"
means having the right to grant, to the maximum extent possible,
whether at the time of the initial grant or subsequently, any and
all of the rights conveyed by this License.
1.10. "Modifications"
means any of the following:
(a) any file in Source Code Form that results from an addition to,
deletion from, or modification of the contents of Covered
Software; or
(b) any new file in Source Code Form that contains any Covered
Software.
1.11. "Patent Claims" of a Contributor
means any patent claim(s), including without limitation, method,
process, and apparatus claims, in any patent Licensable by such
Contributor that would be infringed, but for the grant of the
License, by the making, using, selling, offering for sale, having
made, import, or transfer of either its Contributions or its
Contributor Version.
1.12. "Secondary License"
means either the GNU General Public License, Version 2.0, the GNU
Lesser General Public License, Version 2.1, the GNU Affero General
Public License, Version 3.0, or any later versions of those
licenses.
1.13. "Source Code Form"
means the form of the work preferred for making modifications.
1.14. "You" (or "Your")
means an individual or a legal entity exercising rights under this
License. For legal entities, "You" includes any entity that
controls, is controlled by, or is under common control with You. For
purposes of this definition, "control" means (a) the power, direct
or indirect, to cause the direction or management of such entity,
whether by contract or otherwise, or (b) ownership of more than
fifty percent (50%) of the outstanding shares or beneficial
ownership of such entity.
2. License Grants and Conditions
--------------------------------
2.1. Grants
Each Contributor hereby grants You a world-wide, royalty-free,
non-exclusive license:
(a) under intellectual property rights (other than patent or trademark)
Licensable by such Contributor to use, reproduce, make available,
modify, display, perform, distribute, and otherwise exploit its
Contributions, either on an unmodified basis, with Modifications, or
as part of a Larger Work; and
(b) under Patent Claims of such Contributor to make, use, sell, offer
for sale, have made, import, and otherwise transfer either its
Contributions or its Contributor Version.
2.2. Effective Date
The licenses granted in Section 2.1 with respect to any Contribution
become effective for each Contribution on the date the Contributor first
distributes such Contribution.
2.3. Limitations on Grant Scope
The licenses granted in this Section 2 are the only rights granted under
this License. No additional rights or licenses will be implied from the
distribution or licensing of Covered Software under this License.
Notwithstanding Section 2.1(b) above, no patent license is granted by a
Contributor:
(a) for any code that a Contributor has removed from Covered Software;
or
(b) for infringements caused by: (i) Your and any other third party's
modifications of Covered Software, or (ii) the combination of its
Contributions with other software (except as part of its Contributor
Version); or
(c) under Patent Claims infringed by Covered Software in the absence of
its Contributions.
This License does not grant any rights in the trademarks, service marks,
or logos of any Contributor (except as may be necessary to comply with
the notice requirements in Section 3.4).
2.4. Subsequent Licenses
No Contributor makes additional grants as a result of Your choice to
distribute the Covered Software under a subsequent version of this
License (see Section 10.2) or under the terms of a Secondary License (if
permitted under the terms of Section 3.3).
2.5. Representation
Each Contributor represents that the Contributor believes its
Contributions are its original creation(s) or it has sufficient rights
to grant the rights to its Contributions conveyed by this License.
2.6. Fair Use
This License is not intended to limit any rights You have under
applicable copyright doctrines of fair use, fair dealing, or other
equivalents.
2.7. Conditions
Sections 3.1, 3.2, 3.3, and 3.4 are conditions of the licenses granted
in Section 2.1.
3. Responsibilities
-------------------
3.1. Distribution of Source Form
All distribution of Covered Software in Source Code Form, including any
Modifications that You create or to which You contribute, must be under
the terms of this License. You must inform recipients that the Source
Code Form of the Covered Software is governed by the terms of this
License, and how they can obtain a copy of this License. You may not
attempt to alter or restrict the recipients' rights in the Source Code
Form.
3.2. Distribution of Executable Form
If You distribute Covered Software in Executable Form then:
(a) such Covered Software must also be made available in Source Code
Form, as described in Section 3.1, and You must inform recipients of
the Executable Form how they can obtain a copy of such Source Code
Form by reasonable means in a timely manner, at a charge no more
than the cost of distribution to the recipient; and
(b) You may distribute such Executable Form under the terms of this
License, or sublicense it under different terms, provided that the
license for the Executable Form does not attempt to limit or alter
the recipients' rights in the Source Code Form under this License.
3.3. Distribution of a Larger Work
You may create and distribute a Larger Work under terms of Your choice,
provided that You also comply with the requirements of this License for
the Covered Software. If the Larger Work is a combination of Covered
Software with a work governed by one or more Secondary Licenses, and the
Covered Software is not Incompatible With Secondary Licenses, this
License permits You to additionally distribute such Covered Software
under the terms of such Secondary License(s), so that the recipient of
the Larger Work may, at their option, further distribute the Covered
Software under the terms of either this License or such Secondary
License(s).
3.4. Notices
You may not remove or alter the substance of any license notices
(including copyright notices, patent notices, disclaimers of warranty,
or limitations of liability) contained within the Source Code Form of
the Covered Software, except that You may alter any license notices to
the extent required to remedy known factual inaccuracies.
3.5. Application of Additional Terms
You may choose to offer, and to charge a fee for, warranty, support,
indemnity or liability obligations to one or more recipients of Covered
Software. However, You may do so only on Your own behalf, and not on
behalf of any Contributor. You must make it absolutely clear that any
such warranty, support, indemnity, or liability obligation is offered by
You alone, and You hereby agree to indemnify every Contributor for any
liability incurred by such Contributor as a result of warranty, support,
indemnity or liability terms You offer. You may include additional
disclaimers of warranty and limitations of liability specific to any
jurisdiction.
4. Inability to Comply Due to Statute or Regulation
---------------------------------------------------
If it is impossible for You to comply with any of the terms of this
License with respect to some or all of the Covered Software due to
statute, judicial order, or regulation then You must: (a) comply with
the terms of this License to the maximum extent possible; and (b)
describe the limitations and the code they affect. Such description must
be placed in a text file included with all distributions of the Covered
Software under this License. Except to the extent prohibited by statute
or regulation, such description must be sufficiently detailed for a
recipient of ordinary skill to be able to understand it.
5. Termination
--------------
5.1. The rights granted under this License will terminate automatically
if You fail to comply with any of its terms. However, if You become
compliant, then the rights granted under this License from a particular
Contributor are reinstated (a) provisionally, unless and until such
Contributor explicitly and finally terminates Your grants, and (b) on an
ongoing basis, if such Contributor fails to notify You of the
non-compliance by some reasonable means prior to 60 days after You have
come back into compliance. Moreover, Your grants from a particular
Contributor are reinstated on an ongoing basis if such Contributor
notifies You of the non-compliance by some reasonable means, this is the
first time You have received notice of non-compliance with this License
from such Contributor, and You become compliant prior to 30 days after
Your receipt of the notice.
5.2. If You initiate litigation against any entity by asserting a patent
infringement claim (excluding declaratory judgment actions,
counter-claims, and cross-claims) alleging that a Contributor Version
directly or indirectly infringes any patent, then the rights granted to
You by any and all Contributors for the Covered Software under Section
2.1 of this License shall terminate.
5.3. In the event of termination under Sections 5.1 or 5.2 above, all
end user license agreements (excluding distributors and resellers) which
have been validly granted by You or Your distributors under this License
prior to termination shall survive termination.
************************************************************************
* *
* 6. Disclaimer of Warranty *
* ------------------------- *
* *
* Covered Software is provided under this License on an "as is" *
* basis, without warranty of any kind, either expressed, implied, or *
* statutory, including, without limitation, warranties that the *
* Covered Software is free of defects, merchantable, fit for a *
* particular purpose or non-infringing. The entire risk as to the *
* quality and performance of the Covered Software is with You. *
* Should any Covered Software prove defective in any respect, You *
* (not any Contributor) assume the cost of any necessary servicing, *
* repair, or correction. This disclaimer of warranty constitutes an *
* essential part of this License. No use of any Covered Software is *
* authorized under this License except under this disclaimer. *
* *
************************************************************************
************************************************************************
* *
* 7. Limitation of Liability *
* -------------------------- *
* *
* Under no circumstances and under no legal theory, whether tort *
* (including negligence), contract, or otherwise, shall any *
* Contributor, or anyone who distributes Covered Software as *
* permitted above, be liable to You for any direct, indirect, *
* special, incidental, or consequential damages of any character *
* including, without limitation, damages for lost profits, loss of *
* goodwill, work stoppage, computer failure or malfunction, or any *
* and all other commercial damages or losses, even if such party *
* shall have been informed of the possibility of such damages. This *
* limitation of liability shall not apply to liability for death or *
* personal injury resulting from such party's negligence to the *
* extent applicable law prohibits such limitation. Some *
* jurisdictions do not allow the exclusion or limitation of *
* incidental or consequential damages, so this exclusion and *
* limitation may not apply to You. *
* *
************************************************************************
8. Litigation
-------------
Any litigation relating to this License may be brought only in the
courts of a jurisdiction where the defendant maintains its principal
place of business and such litigation shall be governed by laws of that
jurisdiction, without reference to its conflict-of-law provisions.
Nothing in this Section shall prevent a party's ability to bring
cross-claims or counter-claims.
9. Miscellaneous
----------------
This License represents the complete agreement concerning the subject
matter hereof. If any provision of this License is held to be
unenforceable, such provision shall be reformed only to the extent
necessary to make it enforceable. Any law or regulation which provides
that the language of a contract shall be construed against the drafter
shall not be used to construe this License against a Contributor.
10. Versions of the License
---------------------------
10.1. New Versions
Mozilla Foundation is the license steward. Except as provided in Section
10.3, no one other than the license steward has the right to modify or
publish new versions of this License. Each version will be given a
distinguishing version number.
10.2. Effect of New Versions
You may distribute the Covered Software under the terms of the version
of the License under which You originally received the Covered Software,
or under the terms of any subsequent version published by the license
steward.
10.3. Modified Versions
If you create software not governed by this License, and you want to
create a new license for such software, you may create and use a
modified version of this License if you rename the license and remove
any references to the name of the license steward (except to note that
such modified license differs from this License).
10.4. Distributing Source Code Form that is Incompatible With Secondary
Licenses
If You choose to distribute Source Code Form that is Incompatible With
Secondary Licenses under the terms of this version of the License, the
notice described in Exhibit B of this License must be attached.
Exhibit A - Source Code Form License Notice
-------------------------------------------
This Source Code Form is subject to the terms of the Mozilla Public
License, v. 2.0. If a copy of the MPL was not distributed with this
file, You can obtain one at http://mozilla.org/MPL/2.0/.
If it is not possible or desirable to put the notice in a particular
file, then You may include the notice in a location (such as a LICENSE
file in a relevant directory) where a recipient would be likely to look
for such a notice.
You may add additional accurate notices of copyright ownership.
Exhibit B - "Incompatible With Secondary Licenses" Notice
---------------------------------------------------------
This Source Code Form is "Incompatible With Secondary Licenses", as
defined by the Mozilla Public License, v. 2.0.

2
README.md
View File

@ -1,4 +1,4 @@
# audio-algo-speex # audio-algo-speex
(MPL v2.0) speex dsp algo normalisation wrapper (APACHE 2) speex dsp algo normalisation wrapper
[![Build Status](https://travis-ci.org/musicdsp/audio-algo-speex.svg?branch=master)](https://travis-ci.org/musicdsp/audio-algo-speex) [![Build Status](https://travis-ci.org/musicdsp/audio-algo-speex.svg?branch=master)](https://travis-ci.org/musicdsp/audio-algo-speex)

200
audio/algo/speex/Aec.cpp
View File

@ -1,200 +0,0 @@
/** @file
* @author Edouard DUPIN
* @copyright 2011, Edouard DUPIN, all right reserved
* @license APACHE v2.0 (see license file)
*/
#define speex_POSIX 1
#include <audio/algo/speex/Aec.hpp>
#include <audio/algo/speex/debug.hpp>
#include <cmath>
#include <speex/speex_echo.h>
#include <speex/speex_preprocess.h>
namespace audio {
namespace algo {
namespace speex {
class AecPrivate {
private:
SpeexEchoState* m_speexEchoState = null;
SpeexPreprocessState* m_speexPreprocessState = null;
enum audio::format m_format;
float m_sampleRate;
int8_t m_nbChannel;
etk::Vector<float> m_tmpBufferIn;
etk::Vector<float> m_tmpBufferOut;
int32_t m_frameSize;
uint32_t calculateBlockSize(uint32_t _sampleRate, uint32_t _sizeInMs) {
uint32_t nframes = (_sampleRate * _sizeInMs) / 1000;
uint32_t y = 1 << ((8 * sizeof(uint32_t)) - 2);
if(_sampleRate < 4000) {
AA_SPEEX_INFO("speex: request Sample rate < 4000: " << _sampleRate);
return 32;
}
if(_sizeInMs < 1) {
AA_SPEEX_INFO("speex: request size in ms < 1: " << _sizeInMs);
return 32;
}
// calculate power of 2:
while (y > nframes) {
y >>= 1;
}
return y;
}
public:
AecPrivate(int8_t _nbChannel, float _sampleRate, enum audio::format _format) :
m_format(_format),
m_sampleRate(_sampleRate),
m_nbChannel(_nbChannel) {
bool paramAGC = false;
bool paramDenoise = false;
bool paramEchoSuppress = true;
int32_t paramEchoSuppressAttenuation = -40;
int32_t paramEchoSuppressAttenuationActive = -15;
uint32_t filterSizeMs = 200; // Buffer size in ms [100-500]
uint32_t frameSizeMs = 20; // Frame size in ms [10..20]
m_frameSize = calculateBlockSize(m_sampleRate, frameSizeMs);
AA_SPEEX_INFO("Using framesize: " << m_frameSize);
/*
m_speexEchoState = speex_echo_state_init_mc(m_frameSize,
(m_sampleRate * filterSizeMs) / 1000,
m_nbChannel, // n microphone channel ...
1 // 1 speaker
);
*/
m_speexEchoState = speex_echo_state_init(m_frameSize, calculateBlockSize(m_sampleRate,filterSizeMs));//(m_sampleRate*filterSizeMs)/1000);
if (m_speexEchoState == null) {
AA_SPEEX_ERROR("Can not intanciate speex handle");
return;
}
int sampleRateToInject = _sampleRate;
speex_echo_ctl(m_speexEchoState, SPEEX_ECHO_SET_SAMPLING_RATE, &sampleRateToInject);
if ( paramAGC == true
|| paramDenoise == true
|| paramEchoSuppress == true) {
spx_int32_t tmp;
if (_nbChannel != 1) {
AA_SPEEX_ERROR("support only one channel ... ==> need to create multiple channel instance ...");
return;
}
m_speexPreprocessState = speex_preprocess_state_init(m_frameSize, m_sampleRate);
AA_SPEEX_INFO("Set speex preprocessor AGC=" << paramAGC);
tmp = paramAGC;
speex_preprocess_ctl(m_speexPreprocessState, SPEEX_PREPROCESS_SET_AGC, &tmp);
AA_SPEEX_INFO("Set speex preprocessor DENOISE=" << paramDenoise);
tmp = paramDenoise;
speex_preprocess_ctl(m_speexPreprocessState, SPEEX_PREPROCESS_SET_DENOISE, &tmp);
if (paramEchoSuppress) {
if (paramEchoSuppressAttenuation) {
int32_t tmpEchoSuppressAttenuation;
speex_preprocess_ctl(m_speexPreprocessState, SPEEX_PREPROCESS_GET_ECHO_SUPPRESS, &tmpEchoSuppressAttenuation);
AA_SPEEX_INFO("Set speex preprocessor AEC attenuation=" << paramEchoSuppressAttenuation << " base=" << tmpEchoSuppressAttenuation);
speex_preprocess_ctl(m_speexPreprocessState, SPEEX_PREPROCESS_SET_ECHO_SUPPRESS, &paramEchoSuppressAttenuation);
}
if (paramEchoSuppressAttenuationActive) {
int32_t tmpEchoSuppressAttenuationActive;
speex_preprocess_ctl(m_speexPreprocessState, SPEEX_PREPROCESS_GET_ECHO_SUPPRESS_ACTIVE, &tmpEchoSuppressAttenuationActive);
AA_SPEEX_INFO("Set speex preprocessor AEC attenuation enable=" << paramEchoSuppressAttenuationActive << " base=" << tmpEchoSuppressAttenuationActive);
speex_preprocess_ctl(m_speexPreprocessState, SPEEX_PREPROCESS_SET_ECHO_SUPPRESS_ACTIVE, &paramEchoSuppressAttenuationActive);
}
speex_preprocess_ctl(m_speexPreprocessState, SPEEX_PREPROCESS_SET_ECHO_STATE, m_speexEchoState);
}
} else {
AA_SPEEX_ERROR("request speex with no algorithm");
}
}
~AecPrivate() {
/* TODO : Check this leak ...
if (m_speexPreprocessState) {
speex_preprocess_state_destroy(m_speexPreprocessState);
m_speexPreprocessState = null;
}
if (m_speexEchoState) {
speex_echo_state_destroy(m_speexEchoState);
m_speexEchoState = null;
}
*/
}
/**
* @brief Main input algo process.
* @param[in,out] _output Output data.
* @param[in] _input Input data.
* @param[in] _inputFeedback Input feedback data (all time MONO).
* @param[in] _nbChunk Number of chunk in the input buffer.
* @param[in] _nbChannel Number of channel in the stream.
*/
void process(void* _output, const void* _input, const void* _inputFeedback, size_t _nbChunk) {
if (m_speexEchoState == null) {
AA_SPEEX_ERROR("speex handle is not initialize ==> can not process");
return;
}
switch (m_format) {
case audio::format_int16:
// process APC
speex_echo_cancellation(m_speexEchoState, (const spx_int16_t*)_input, (const spx_int16_t*)_inputFeedback, (spx_int16_t*)_output);
// apply NR after AEC
if (m_speexPreprocessState != null) {
speex_preprocess_run(m_speexPreprocessState, (spx_int16_t*) _output);
}
return;
default:
AA_SPEEX_ERROR("Can not Limit with unsupported format : " << m_format);
break;
}
}
int32_t getOptimalFrameSize() {
return m_frameSize;
}
};
}
}
}
void audio::algo::speex::Aec::init(int8_t _nbChannel, float _sampleRate, enum audio::format _format) {
m_private.reset();
m_private = ememory::makeShared<audio::algo::speex::AecPrivate>(_nbChannel, _sampleRate, _format);
}
etk::Vector<float> audio::algo::speex::Aec::getSupportedSampleRate() {
etk::Vector<float> out;
out.pushBack(4000);
out.pushBack(8000);
out.pushBack(16000);
out.pushBack(32000);
out.pushBack(48000);
return out;
}
etk::Vector<enum audio::format> audio::algo::speex::Aec::getSupportedFormat() {
return getNativeSupportedFormat();
}
etk::Vector<enum audio::format> audio::algo::speex::Aec::getNativeSupportedFormat() {
etk::Vector<enum audio::format> out;
//out.pushBack(audio::format_float);
out.pushBack(audio::format_int16);
return out;
}
void audio::algo::speex::Aec::process(void* _output, const void* _input, const void* _inputFeedback, size_t _nbChunk) {
if (m_private == null) {
AA_SPEEX_ERROR("Algo is not initialized...");
}
m_private->process(_output, _input, _inputFeedback, _nbChunk);
}
int32_t audio::algo::speex::Aec::getOptimalFrameSize() {
if (m_private == null) {
AA_SPEEX_ERROR("Algo is not initialized...");
return 32;
}
return m_private->getOptimalFrameSize();
}

61
audio/algo/speex/Aec.hpp
View File

@ -1,61 +0,0 @@
/** @file
* @author Edouard DUPIN
* @copyright 2011, Edouard DUPIN, all right reserved
* @license APACHE v2.0 (see license file)
*/
#pragma once
#include <etk/types.hpp>
#include <audio/format.hpp>
#include <chrono>
#include <ememory/memory.hpp>
#include <vector>
namespace audio {
namespace algo {
namespace speex {
class AecPrivate;
class Aec {
public:
Aec() = default;
virtual ~Aec() = default;
public:
/**
* @brief Initialize the Algorithm
* @param[in] _nbChannel Number of channel in the stream.
* @param[in] _sampleRate Sample rate.
* @param[in] _format Input/output data format.
*/
virtual void init(int8_t _nbChannel, float _sampleRate, enum audio::format _format = audio::format_float);
/**
* @brief Get list of samplerate suported.
* @return list of supported samplerate
*/
virtual etk::Vector<float> getSupportedSampleRate();
/**
* @brief Get list of format suported in input.
* @return list of supported format
*/
virtual etk::Vector<enum audio::format> getSupportedFormat();
/**
* @brief Get list of algorithm format suported. No format convertion.
* @return list of supported format
*/
virtual etk::Vector<enum audio::format> getNativeSupportedFormat();
/**
* @brief Main input algo process.
* @param[in,out] _output Output data.
* @param[in] _input Input data.
* @param[in] _inputFeedback Input feedback data (all time MONO).
* @param[in] _nbChunk Number of chunk in the input buffer.
* @param[in] _nbChannel Number of channel in the stream.
*/
virtual void process(void* _output, const void* _input, const void* _inputFeedback, size_t _nbChunk);
int32_t getOptimalFrameSize();
protected:
ememory::SharedPtr<AecPrivate> m_private; //!< private data.
};
}
}
}

32
audio/algo/speex/Resampler.cpp
View File

@ -1,12 +1,12 @@
/** @file /** @file
* @author Edouard DUPIN * @author Edouard DUPIN
* @copyright 2011, Edouard DUPIN, all right reserved * @copyright 2011, Edouard DUPIN, all right reserved
* @license MPL v2.0 (see license file) * @license APACHE v2.0 (see license file)
*/ */
#include <audio/algo/speex/Resampler.hpp> #include <audio/algo/speex/Resampler.h>
#include <audio/algo/speex/debug.hpp> #include <audio/algo/speex/debug.h>
#include <cmath> #include <cmath>
#ifdef HAVE_SPEEX_DSP #ifdef HAVE_SPEEX_DSP
#include <speex/speex_resampler.h> #include <speex/speex_resampler.h>
@ -24,13 +24,13 @@ namespace audio {
public: public:
ResamplerPrivate(int8_t _nbChannel, float _inputSampleRate, float _outputSampleRate, int8_t _quality, enum audio::format _format) : ResamplerPrivate(int8_t _nbChannel, float _inputSampleRate, float _outputSampleRate, int8_t _quality, enum audio::format _format) :
#ifdef HAVE_SPEEX_DSP #ifdef HAVE_SPEEX_DSP
m_speexResampler(null), m_speexResampler(nullptr),
#endif #endif
m_format(_format) { m_format(_format) {
#ifdef HAVE_SPEEX_DSP #ifdef HAVE_SPEEX_DSP
if (m_speexResampler != null) { if (m_speexResampler != nullptr) {
speex_resampler_destroy(m_speexResampler); speex_resampler_destroy(m_speexResampler);
m_speexResampler = null; m_speexResampler = nullptr;
} }
AA_SPEEX_DEBUG("Create resampler for : " << _inputSampleRate << " to " << _outputSampleRate); AA_SPEEX_DEBUG("Create resampler for : " << _inputSampleRate << " to " << _outputSampleRate);
int err = 0; int err = 0;
@ -45,9 +45,9 @@ namespace audio {
~ResamplerPrivate() { ~ResamplerPrivate() {
#ifdef HAVE_SPEEX_DSP #ifdef HAVE_SPEEX_DSP
if (m_speexResampler != null) { if (m_speexResampler != nullptr) {
speex_resampler_destroy(m_speexResampler); speex_resampler_destroy(m_speexResampler);
m_speexResampler = null; m_speexResampler = nullptr;
} }
#endif #endif
} }
@ -78,7 +78,6 @@ namespace audio {
break; break;
case audio::format_float: case audio::format_float:
{ {
AA_SPEEX_ERROR("RESAMPLE: " << _nbChunk << " ==> " << _nbChunkOut);
uint32_t nbChunkInput = _nbChunk; uint32_t nbChunkInput = _nbChunk;
uint32_t nbChunkOutput = _nbChunkOut; uint32_t nbChunkOutput = _nbChunkOut;
int ret = speex_resampler_process_interleaved_float(m_speexResampler, int ret = speex_resampler_process_interleaved_float(m_speexResampler,
@ -86,7 +85,6 @@ namespace audio {
&nbChunkInput, &nbChunkInput,
reinterpret_cast<float*>(_output), reinterpret_cast<float*>(_output),
&nbChunkOutput); &nbChunkOutput);
AA_SPEEX_ERROR("RESAMPLE: " << nbChunkInput << " ==> " << nbChunkOutput << " DONE");
// Check all input and output ... // Check all input and output ...
if (nbChunkInput != _nbChunk) { if (nbChunkInput != _nbChunk) {
AA_SPEEX_ERROR("inputSize (not all read ...) proceed=" << nbChunkInput << " requested=" << _nbChunk); AA_SPEEX_ERROR("inputSize (not all read ...) proceed=" << nbChunkInput << " requested=" << _nbChunk);
@ -127,20 +125,20 @@ void audio::algo::speex::Resampler::init(int8_t _nbChannel, float _inputSampleRa
m_private = ememory::makeShared<audio::algo::speex::ResamplerPrivate>(_nbChannel, _inputSampleRate, _outputSampleRate, _quality, _format); m_private = ememory::makeShared<audio::algo::speex::ResamplerPrivate>(_nbChannel, _inputSampleRate, _outputSampleRate, _quality, _format);
} }
etk::Vector<enum audio::format> audio::algo::speex::Resampler::getSupportedFormat() { std::vector<enum audio::format> audio::algo::speex::Resampler::getSupportedFormat() {
etk::Vector<enum audio::format> out = getNativeSupportedFormat(); std::vector<enum audio::format> out = getNativeSupportedFormat();
return out; return out;
} }
etk::Vector<enum audio::format> audio::algo::speex::Resampler::getNativeSupportedFormat() { std::vector<enum audio::format> audio::algo::speex::Resampler::getNativeSupportedFormat() {
etk::Vector<enum audio::format> out; std::vector<enum audio::format> out;
//out.pushBack(audio::format_float); ==> sppex dsp only compille in fixpoint, of float ... not at the same time ... out.push_back(audio::format_float);
out.pushBack(audio::format_int16); out.push_back(audio::format_int16);
return out; return out;
} }
void audio::algo::speex::Resampler::process(void* _output, size_t& _nbChunkOut, const void* _input, size_t _nbChunk) { void audio::algo::speex::Resampler::process(void* _output, size_t& _nbChunkOut, const void* _input, size_t _nbChunk) {
if (m_private == null) { if (m_private == nullptr) {
AA_SPEEX_ERROR("Algo is not initialized..."); AA_SPEEX_ERROR("Algo is not initialized...");
} }
m_private->process(_output, _nbChunkOut, _input, _nbChunk); m_private->process(_output, _nbChunkOut, _input, _nbChunk);

16
audio/algo/speex/Resampler.hpp → audio/algo/speex/Resampler.h
View File

@ -1,15 +1,15 @@
/** @file /** @file
* @author Edouard DUPIN * @author Edouard DUPIN
* @copyright 2011, Edouard DUPIN, all right reserved * @copyright 2011, Edouard DUPIN, all right reserved
* @license MPL v2.0 (see license file) * @license APACHE v2.0 (see license file)
*/ */
#pragma once #pragma once
#include <etk/types.hpp> #include <etk/types.h>
#include <audio/format.hpp> #include <audio/format.h>
#include <echrono/Steady.hpp> #include <chrono>
#include <ememory/memory.hpp> #include <ememory/memory.h>
#include <etk/Vector.hpp> #include <vector>
namespace audio { namespace audio {
namespace algo { namespace algo {
@ -33,12 +33,12 @@ namespace audio {
* @brief Get list of format suported in input. * @brief Get list of format suported in input.
* @return list of supported format * @return list of supported format
*/ */
virtual etk::Vector<enum audio::format> getSupportedFormat(); virtual std::vector<enum audio::format> getSupportedFormat();
/** /**
* @brief Get list of algorithm format suported. No format convertion. * @brief Get list of algorithm format suported. No format convertion.
* @return list of supported format * @return list of supported format
*/ */
virtual etk::Vector<enum audio::format> getNativeSupportedFormat(); virtual std::vector<enum audio::format> getNativeSupportedFormat();
/** /**
* @brief Main input algo process. * @brief Main input algo process.
* @param[in,out] _output Output data. * @param[in,out] _output Output data.

114
audio/algo/speex/Vad.cpp
View File

@ -1,114 +0,0 @@
/** @file
* @author Edouard DUPIN
* @copyright 2011, Edouard DUPIN, all right reserved
* @license APACHE v2.0 (see license file)
*/
#define speex_POSIX 1
#include <audio/algo/speex/Vad.hpp>
#include <audio/algo/speex/debug.hpp>
#include <cmath>
#include <webrtc/common_audio/vad/include/webrtc_vad.h>
namespace audio {
namespace algo {
namespace speex {
class VadPrivate {
private:
VadInst *m_vad = null;
bool m_voiceDetected = false;
uint32_t calculateBlockSize(uint32_t _sampleRate, uint32_t _sizeInMs) {
return 0;
}
public:
VadPrivate() {
WebRtcVad_Create(&m_vad);
WebRtcVad_Init(m_vad);
}
~VadPrivate() {
/* TODO : Check this leak ...
if (m_speexPreprocessState) {
speex_preprocess_state_destroy(m_speexPreprocessState);
m_speexPreprocessState = null;
}
if (m_speexEchoState) {
speex_echo_state_destroy(m_speexEchoState);
m_speexEchoState = null;
}
*/
}
/**
* @brief Main input algo process.
* @param[in,out] _output Output data.
* @param[in] _input Input data.
* @param[in] _inputFeedback Input feedback data (all time MONO).
* @param[in] _nbChunk Number of chunk in the input buffer.
* @param[in] _nbChannel Number of channel in the stream.
*/
void process(const void* _input, size_t _nbChunk) {
if (m_vad == null) {
AA_SPEEX_ERROR("speex handle is not initialize ==> can not process");
return;
}
m_voiceDetected = WebRtcVad_Process(m_vad, 16000, (const int16_t*)_input, _nbChunk);
}
int32_t getOptimalFrameSize() {
return 160;
}
bool getVoiceDetected() {
return m_voiceDetected;
}
};
}
}
}
void audio::algo::speex::Vad::init(int8_t _nbChannel, float _sampleRate, enum audio::format _format) {
m_private.reset();
m_private = ememory::makeShared<audio::algo::speex::VadPrivate>();
}
etk::Vector<float> audio::algo::speex::Vad::getSupportedSampleRate() {
etk::Vector<float> out;
out.pushBack(16000);
return out;
}
etk::Vector<enum audio::format> audio::algo::speex::Vad::getSupportedFormat() {
return getNativeSupportedFormat();
}
etk::Vector<enum audio::format> audio::algo::speex::Vad::getNativeSupportedFormat() {
etk::Vector<enum audio::format> out;
out.pushBack(audio::format_int16);
return out;
}
/// set 10 ms ==> 160 sample
void audio::algo::speex::Vad::process(const void* _input, size_t _nbChunk) {
if (m_private == null) {
AA_SPEEX_ERROR("Algo is not initialized...");
}
m_private->process(_input, _nbChunk);
}
int32_t audio::algo::speex::Vad::getOptimalFrameSize() {
if (m_private == null) {
AA_SPEEX_ERROR("Algo is not initialized...");
return 32;
}
return m_private->getOptimalFrameSize();
}
bool audio::algo::speex::Vad::getVoiceDetected() {
if (m_private == null) {
AA_SPEEX_ERROR("Algo is not initialized...");
return 32;
}
return m_private->getVoiceDetected();
}

64
audio/algo/speex/Vad.hpp
View File

@ -1,64 +0,0 @@
/** @file
* @author Edouard DUPIN
* @copyright 2011, Edouard DUPIN, all right reserved
* @license APACHE v2.0 (see license file)
*/
#pragma once
#include <etk/types.hpp>
#include <audio/format.hpp>
#include <chrono>
#include <ememory/memory.hpp>
#include <vector>
namespace audio {
namespace algo {
namespace speex {
class VadPrivate;
class Vad {
public:
Vad() = default;
virtual ~Vad() = default;
public:
/**
* @brief Initialize the Algorithm
* @param[in] _nbChannel Number of channel in the stream.
* @param[in] _sampleRate Sample rate.
* @param[in] _format Input/output data format.
*/
virtual void init(int8_t _nbChannel, float _sampleRate, enum audio::format _format = audio::format_float);
/**
* @brief Get list of samplerate suported.
* @return list of supported samplerate
*/
virtual etk::Vector<float> getSupportedSampleRate();
/**
* @brief Get list of format suported in input.
* @return list of supported format
*/
virtual etk::Vector<enum audio::format> getSupportedFormat();
/**
* @brief Get list of algorithm format suported. No format convertion.
* @return list of supported format
*/
virtual etk::Vector<enum audio::format> getNativeSupportedFormat();
/**
* @brief Main input algo process.
* @param[in,out] _output Output data.
* @param[in] _input Input data.
* @param[in] _inputFeedback Input feedback data (all time MONO).
* @param[in] _nbChunk Number of chunk in the input buffer.
* @param[in] _nbChannel Number of channel in the stream.
*/
virtual void process(const void* _input, size_t _nbChunk);
bool getVoiceDetected();
int32_t getOptimalFrameSize();
protected:
ememory::SharedPtr<VadPrivate> m_private; //!< private data.
};
}
}
}

4
audio/algo/speex/debug.cpp
View File

@ -1,10 +1,10 @@
/** @file /** @file
* @author Edouard DUPIN * @author Edouard DUPIN
* @copyright 2011, Edouard DUPIN, all right reserved * @copyright 2011, Edouard DUPIN, all right reserved
* @license MPL v2.0 (see license file) * @license APACHE v2.0 (see license file)
*/ */
#include "debug.hpp" #include "debug.h"
int32_t audio::algo::speex::getLogId() { int32_t audio::algo::speex::getLogId() {

4
audio/algo/speex/debug.hpp → audio/algo/speex/debug.h
View File

@ -1,11 +1,11 @@
/** @file /** @file
* @author Edouard DUPIN * @author Edouard DUPIN
* @copyright 2011, Edouard DUPIN, all right reserved * @copyright 2011, Edouard DUPIN, all right reserved
* @license MPL v2.0 (see license file) * @license APACHE v2.0 (see license file)
*/ */
#pragma once #pragma once
#include <elog/log.hpp> #include <elog/log.h>
namespace audio { namespace audio {
namespace algo { namespace algo {

14
lutin_audio-algo-speex-test.py
View File

@ -1,5 +1,5 @@
#!/usr/bin/python #!/usr/bin/python
import realog.debug as debug import lutin.module as module
import lutin.tools as tools import lutin.tools as tools
@ -13,7 +13,7 @@ def get_desc():
return "test for speex ALGO" return "test for speex ALGO"
def get_licence(): def get_licence():
return "MPL-2" return "APACHE-2"
def get_compagny_type(): def get_compagny_type():
return "com" return "com"
@ -24,15 +24,13 @@ def get_compagny_name():
def get_maintainer(): def get_maintainer():
return "authors.txt" return "authors.txt"
def configure(target, my_module): def create(target, module_name):
my_module = module.Module(__file__, module_name, get_type())
my_module.add_src_file([ my_module.add_src_file([
'test/main.cpp' 'test/main.cpp'
]) ])
my_module.add_depend([ my_module.add_depend(['audio-algo-speex', 'test-debug'])
'audio-algo-speex', return my_module
'test-debug'
])
return True

25
lutin_audio-algo-speex.py
View File

@ -1,5 +1,5 @@
#!/usr/bin/python #!/usr/bin/python
import realog.debug as debug import lutin.module as module
import lutin.tools as tools import lutin.tools as tools
@ -10,7 +10,7 @@ def get_desc():
return "speex algos wrapper" return "speex algos wrapper"
def get_licence(): def get_licence():
return "MPL-2" return "APACHE-2"
def get_compagny_type(): def get_compagny_type():
return "com" return "com"
@ -24,26 +24,19 @@ def get_maintainer():
def get_version(): def get_version():
return "version.txt" return "version.txt"
def configure(target, my_module): def create(target, module_name):
my_module = module.Module(__file__, module_name, get_type())
my_module.add_src_file([ my_module.add_src_file([
'audio/algo/speex/debug.cpp', 'audio/algo/speex/debug.cpp',
'audio/algo/speex/Resampler.cpp', 'audio/algo/speex/Resampler.cpp'
'audio/algo/speex/Aec.cpp',
'audio/algo/speex/Vad.cpp',
]) ])
my_module.add_header_file([ my_module.add_header_file([
'audio/algo/speex/Resampler.hpp', 'audio/algo/speex/Resampler.h'
'audio/algo/speex/Aec.hpp',
'audio/algo/speex/Vad.hpp',
])
my_module.add_depend([
'etk',
'audio',
'webrtc',
]) ])
my_module.add_depend(['etk', 'audio'])
my_module.add_optionnal_depend('speex-dsp', ["c++", "-DHAVE_SPEEX_DSP"]) my_module.add_optionnal_depend('speex-dsp', ["c++", "-DHAVE_SPEEX_DSP"])
my_module.add_path(".") my_module.add_path(tools.get_current_path(__file__))
return True return my_module

321
test/main.cpp
View File

@ -1,57 +1,53 @@
/** @file /** @file
* @author Edouard DUPIN * @author Edouard DUPIN
* @copyright 2011, Edouard DUPIN, all right reserved * @copyright 2011, Edouard DUPIN, all right reserved
* @license MPL v2.0 (see license file) * @license APACHE v2.0 (see license file)
*/ */
#include <test-debug/debug.hpp> #include <test-debug/debug.h>
#include <etk/etk.hpp> #include <etk/etk.h>
#include <etk/uri/uri.hpp> #include <audio/algo/speex/Resampler.h>
#include <audio/algo/speex/Resampler.hpp> #include <etk/os/FSNode.h>
#include <audio/algo/speex/Aec.hpp> #include <chrono>
#include <echrono/Steady.hpp>
#include <ethread/Thread.hpp>
#include <ethread/tools.hpp>
#include <unistd.h>
class Performance { class Performance {
private: private:
echrono::Steady m_timeStart; std::chrono::steady_clock::time_point m_timeStart;
echrono::Steady m_timeStop; std::chrono::steady_clock::time_point m_timeStop;
echrono::Duration m_totalTimeProcessing; std::chrono::nanoseconds m_totalTimeProcessing;
echrono::Duration m_minProcessing; std::chrono::nanoseconds m_minProcessing;
echrono::Duration m_maxProcessing; std::chrono::nanoseconds m_maxProcessing;
int32_t m_totalIteration; int32_t m_totalIteration;
public: public:
Performance() : Performance() :
m_totalTimeProcessing(0), m_totalTimeProcessing(0),
m_minProcessing(int64_t(99999999999999LL)), m_minProcessing(99999999999999LL),
m_maxProcessing(0), m_maxProcessing(0),
m_totalIteration(0) { m_totalIteration(0) {
} }
void tic() { void tic() {
m_timeStart = echrono::Steady::now(); m_timeStart = std::chrono::steady_clock::now();
} }
void toc() { void toc() {
m_timeStop = echrono::Steady::now(); m_timeStop = std::chrono::steady_clock::now();
echrono::Duration time = m_timeStop - m_timeStart; std::chrono::nanoseconds time = m_timeStop - m_timeStart;
m_minProcessing = etk::min(m_minProcessing, time); m_minProcessing = std::min(m_minProcessing, time);
m_maxProcessing = etk::max(m_maxProcessing, time); m_maxProcessing = std::max(m_maxProcessing, time);
m_totalTimeProcessing += time; m_totalTimeProcessing += time;
m_totalIteration++; m_totalIteration++;
} }
echrono::Duration getTotalTimeProcessing() { std::chrono::nanoseconds getTotalTimeProcessing() {
return m_totalTimeProcessing; return m_totalTimeProcessing;
} }
echrono::Duration getMinProcessing() { std::chrono::nanoseconds getMinProcessing() {
return m_minProcessing; return m_minProcessing;
} }
echrono::Duration getMaxProcessing() { std::chrono::nanoseconds getMaxProcessing() {
return m_maxProcessing; return m_maxProcessing;
} }
int32_t getTotalIteration() { int32_t getTotalIteration() {
@ -61,9 +57,9 @@ class Performance {
}; };
float performanceResamplerStepFloat(float _sampleRateIn, float _sampleRateOut, int8_t _quality) { float performanceResamplerStepFloat(float _sampleRateIn, float _sampleRateOut, int8_t _quality) {
etk::Vector<float> input; std::vector<float> input;
input.resize(1024, 0); input.resize(1024, 0);
etk::Vector<float> output; std::vector<float> output;
output.resize(input.size()*10, 0); output.resize(input.size()*10, 0);
double sampleRate = _sampleRateIn; double sampleRate = _sampleRateIn;
{ {
@ -86,24 +82,24 @@ float performanceResamplerStepFloat(float _sampleRateIn, float _sampleRateOut, i
size_t sizeOut = output.size(); size_t sizeOut = output.size();
algo.process(&output[0], sizeOut, &input[0], input.size()); algo.process(&output[0], sizeOut, &input[0], input.size());
perfo.toc(); perfo.toc();
ethread::sleepMilliSeconds((1)); usleep(1000);
} }
TEST_INFO(" blockSize=" << input.size() << " sample"); TEST_INFO(" blockSize=" << input.size() << " sample");
TEST_INFO(" min < avg < max =" << perfo.getMinProcessing() << " < " TEST_INFO(" min < avg < max =" << perfo.getMinProcessing().count() << "ns < "
<< perfo.getTotalTimeProcessing().get()/perfo.getTotalIteration() << "ns < " << perfo.getTotalTimeProcessing().count()/perfo.getTotalIteration() << "ns < "
<< perfo.getMaxProcessing()); << perfo.getMaxProcessing().count() << "ns ");
float avg = (float(((perfo.getTotalTimeProcessing().get()/perfo.getTotalIteration())*sampleRate)/double(input.size()))/1000000000.0)*100.0; float avg = (float(((perfo.getTotalTimeProcessing().count()/perfo.getTotalIteration())*sampleRate)/double(input.size()))/1000000000.0)*100.0;
TEST_INFO(" min < avg < max= " << (float((perfo.getMinProcessing().get()*sampleRate)/double(input.size()))/1000000000.0)*100.0 << "% < " TEST_INFO(" min < avg < max= " << (float((perfo.getMinProcessing().count()*sampleRate)/double(input.size()))/1000000000.0)*100.0 << "% < "
<< avg << "% < " << avg << "% < "
<< (float((perfo.getMaxProcessing().get()*sampleRate)/double(input.size()))/1000000000.0)*100.0 << "%"); << (float((perfo.getMaxProcessing().count()*sampleRate)/double(input.size()))/1000000000.0)*100.0 << "%");
TEST_PRINT("float : " << _sampleRateIn << " -> " << _sampleRateOut << " quality=" << int32_t(_quality) << " : " << avg << "%"); TEST_PRINT("float : " << _sampleRateIn << " -> " << _sampleRateOut << " quality=" << int32_t(_quality) << " : " << avg << "%");
return avg; return avg;
} }
float performanceResamplerStepI16(float _sampleRateIn, float _sampleRateOut, int8_t _quality) { float performanceResamplerStepI16(float _sampleRateIn, float _sampleRateOut, int8_t _quality) {
etk::Vector<int16_t> input; std::vector<int16_t> input;
input.resize(1024, 0); input.resize(1024, 0);
etk::Vector<int16_t> output; std::vector<int16_t> output;
output.resize(input.size()*10, 0); output.resize(input.size()*10, 0);
double sampleRate = _sampleRateIn; double sampleRate = _sampleRateIn;
{ {
@ -126,16 +122,16 @@ float performanceResamplerStepI16(float _sampleRateIn, float _sampleRateOut, int
size_t sizeOut = output.size(); size_t sizeOut = output.size();
algo.process(&output[0], sizeOut, &input[0], input.size()); algo.process(&output[0], sizeOut, &input[0], input.size());
perfo.toc(); perfo.toc();
ethread::sleepMilliSeconds((1)); usleep(1000);
} }
TEST_INFO(" blockSize=" << input.size() << " sample"); TEST_INFO(" blockSize=" << input.size() << " sample");
TEST_INFO(" min < avg < max =" << perfo.getMinProcessing() << " < " TEST_INFO(" min < avg < max =" << perfo.getMinProcessing().count() << "ns < "
<< perfo.getTotalTimeProcessing().get()/perfo.getTotalIteration() << "ns < " << perfo.getTotalTimeProcessing().count()/perfo.getTotalIteration() << "ns < "
<< perfo.getMaxProcessing()); << perfo.getMaxProcessing().count() << "ns ");
float avg = (float(((perfo.getTotalTimeProcessing().get()/perfo.getTotalIteration())*sampleRate)/double(input.size()))/1000000000.0)*100.0; float avg = (float(((perfo.getTotalTimeProcessing().count()/perfo.getTotalIteration())*sampleRate)/double(input.size()))/1000000000.0)*100.0;
TEST_INFO(" min < avg < max= " << (float((perfo.getMinProcessing().get()*sampleRate)/double(input.size()))/1000000000.0)*100.0 << "% < " TEST_INFO(" min < avg < max= " << (float((perfo.getMinProcessing().count()*sampleRate)/double(input.size()))/1000000000.0)*100.0 << "% < "
<< avg << "% < " << avg << "% < "
<< (float((perfo.getMaxProcessing().get()*sampleRate)/double(input.size()))/1000000000.0)*100.0 << "%"); << (float((perfo.getMaxProcessing().count()*sampleRate)/double(input.size()))/1000000000.0)*100.0 << "%");
TEST_PRINT("int16_t : " << _sampleRateIn << " -> " << _sampleRateOut << " quality=" << int32_t(_quality) << " : " << avg << "%"); TEST_PRINT("int16_t : " << _sampleRateIn << " -> " << _sampleRateOut << " quality=" << int32_t(_quality) << " : " << avg << "%");
return avg; return avg;
} }
@ -167,99 +163,24 @@ void performanceResampler() {
modeFloat = performanceResamplerStepFloat(48000, 8000, iii); modeFloat = performanceResamplerStepFloat(48000, 8000, iii);
modeI16 = performanceResamplerStepI16(48000, 8000, iii); modeI16 = performanceResamplerStepI16(48000, 8000, iii);
} }
}
etk::Vector<int16_t> loadDataI16(etk::Uri _uri, int32_t _nbChannel, int32_t _selectChannel, bool _formatFileInteger16, int32_t _delaySample = 0) {
TEST_INFO("Read : '" << _uri << "'");
etk::Vector<int16_t> out;
for (int32_t iii=0; iii<_delaySample; ++iii) {
out.pushBack(0);
}
ememory::SharedPtr<etk::io::Interface> fileIO = etk::uri::get(_uri);
if (fileIO->open(etk::io::OpenMode::Read) == false) {
return out;
}
if (_uri.getPath().getExtention() == "wav") {
// remove the first 44 bytes
fileIO->seek(44, etk::io::SeekMode::Start);
}
if (_formatFileInteger16 == true) {
etk::Vector<int16_t> tmpData = fileIO->readAll<int16_t>();
for (int32_t iii=0; iii<tmpData.size(); iii+=_nbChannel) {
out.pushBack(tmpData[iii+_selectChannel]);
}
} else {
etk::Vector<float> tmpData = fileIO->readAll<float>();
for (int32_t iii=0; iii<tmpData.size(); iii+=_nbChannel) {
double val = double(tmpData[iii+_selectChannel])*32768.0;
if (val >= 32767.0) {
out.pushBack(32767);
} else if (val <= -32768.0) {
out.pushBack(-32768);
} else {
out.pushBack(int16_t(val));
}
}
}
fileIO->close();
TEST_INFO(" " << out.size() << " samples");
return out;
}
etk::Vector<float> loadDataFloat(etk::Uri _uri, int32_t _nbChannel, int32_t _selectChannel, bool _formatFileInteger16, int32_t _delaySample = 0) {
TEST_INFO("Read : '" << _uri << "'");
etk::Vector<float> out;
for (int32_t iii=0; iii<_delaySample; ++iii) {
out.pushBack(0.0);
}
ememory::SharedPtr<etk::io::Interface> fileIO = etk::uri::get(_uri);
if (fileIO->open(etk::io::OpenMode::Read) == false) {
return out;
}
if (_uri.getPath().getExtention() == "wav") {
// remove the first 44 bytes
fileIO->seek(44, etk::io::SeekMode::Start);
}
if (_formatFileInteger16 == true) {
etk::Vector<int16_t> tmpData = fileIO->readAll<int16_t>();
for (int32_t iii=0; iii<tmpData.size(); iii+=_nbChannel) {
out.pushBack(double(tmpData[iii+_selectChannel])/32768.0);
}
} else {
etk::Vector<float> tmpData = fileIO->readAll<float>();
for (int32_t iii=0; iii<tmpData.size(); iii+=_nbChannel) {
out.pushBack(tmpData[iii+_selectChannel]);
}
}
fileIO->close();
TEST_INFO(" " << out.size() << " samples");
return out;
} }
int main(int _argc, const char** _argv) { int main(int _argc, const char** _argv) {
// the only one init for etk: // the only one init for etk:
etk::init(_argc, _argv); etk::init(_argc, _argv);
etk::Path inputName = ""; std::string inputName = "";
etk::Path feedbackName = ""; std::string outputName = "output.raw";
etk::Path outputName = "output.raw";
bool performance = false; bool performance = false;
bool perf = false; bool perf = false;
int64_t sampleRateIn = 48000; int64_t sampleRateIn = 48000;
int64_t sampleRateOut = 48000; int64_t sampleRateOut = 48000;
int32_t nbChan = 1; int32_t nbChan = 1;
int32_t quality = 4; int32_t quality = 4;
etk::String test = ""; std::string test = "";
bool formatFileInteger16 = true;
int32_t inputNumberChannel = 1;
int32_t inputSelectChannel = 0;
int32_t inputSampleDelay = 0;
int32_t feedbackNumberChannel = 1;
int32_t feedbackSelectChannel = 0;
int32_t feedbackSampleDelay = 0;
for (int32_t iii=0; iii<_argc ; ++iii) { for (int32_t iii=0; iii<_argc ; ++iii) {
etk::String data = _argv[iii]; std::string data = _argv[iii];
if (etk::start_with(data,"--in=")) { if (etk::start_with(data,"--in=")) {
inputName = &data[5]; inputName = &data[5];
} else if (etk::start_with(data,"--out=")) { } else if (etk::start_with(data,"--out=")) {
@ -271,94 +192,34 @@ int main(int _argc, const char** _argv) {
} else if (etk::start_with(data,"--test=")) { } else if (etk::start_with(data,"--test=")) {
data = &data[7]; data = &data[7];
sampleRateIn = etk::string_to_int32_t(data); sampleRateIn = etk::string_to_int32_t(data);
} else if (etk::start_with(data,"--format=")) {
if (data == "--format=i16") {
formatFileInteger16 = true;
} else if (data == "--format=float") {
formatFileInteger16 = false;
} else {
TEST_CRITICAL("unsuported format");
}
} else if (etk::start_with(data,"--in-filter=")) {
etk::String tmpData = &data[12];
inputNumberChannel = tmpData.size();
for (int32_t iii = 0; iii< tmpData.size(); ++iii) {
if (tmpData[iii] == '1') {
inputSelectChannel = iii;
TEST_INFO("SELECT input channel : " << inputNumberChannel+1 << " / " << tmpData.size());
break;
}
}
} else if (etk::start_with(data,"--sample-rate-in=")) { } else if (etk::start_with(data,"--sample-rate-in=")) {
data = &data[17]; data = &data[17];
sampleRateIn = etk::string_to_int32_t(data); sampleRateIn = etk::string_to_int32_t(data);
// **************************************************** } else if (etk::start_with(data,"--sample-rate-out=")) {
// ** RESAMPLING section
// ****************************************************
} else if ( test == "RESAMPLING"
&& etk::start_with(data,"--sample-rate-out=")) {
data = &data[18]; data = &data[18];
sampleRateOut = etk::string_to_int32_t(data); sampleRateOut = etk::string_to_int32_t(data);
} else if ( test == "RESAMPLING" } else if (etk::start_with(data,"--nb=")) {
&& etk::start_with(data,"--nb=")) {
data = &data[5]; data = &data[5];
nbChan = etk::string_to_int32_t(data); nbChan = etk::string_to_int32_t(data);
} else if ( test == "RESAMPLING" } else if (etk::start_with(data,"--quality=")) {
&& etk::start_with(data,"--quality=")) {
data = &data[10]; data = &data[10];
quality = etk::string_to_int32_t(data); quality = etk::string_to_int32_t(data);
// ****************************************************
// ** AEC section
// ****************************************************
} else if ( test == "AEC"
&& etk::start_with(data,"--fb-filter=")) {
etk::String tmpData = &data[12];
feedbackNumberChannel = tmpData.size();
for (int32_t iii = 0; iii< tmpData.size(); ++iii) {
if (tmpData[iii] == '1') {
feedbackSelectChannel = iii;
TEST_INFO("SELECT FB channel : " << feedbackSelectChannel+1 << " / " << tmpData.size());
break;
}
}
} else if ( test == "AEC"
&& etk::start_with(data,"--fb=")) {
feedbackName = &data[5];
} else if ( test == "AEC"
&& etk::start_with(data,"--fb-delay=")) {
data = &data[11];
feedbackSampleDelay = etk::string_to_int32_t(data);
} else if ( test == "AEC"
&& etk::start_with(data,"--in-delay=")) {
data = &data[11];
inputSampleDelay = etk::string_to_int32_t(data);
} else if ( data == "-h" } else if ( data == "-h"
|| data == "--help") { || data == "--help") {
TEST_PRINT("Help : "); TEST_PRINT("Help : ");
TEST_PRINT(" ./xxx --fb=file.raw --mic=file.raw"); TEST_PRINT(" ./xxx --fb=file.raw --mic=file.raw");
TEST_PRINT(" --in=YYY.raw input file"); TEST_PRINT(" --in=YYY.raw input file");
TEST_PRINT(" --in-filter=xxx Select the channel desired in the input stream (n*0 for each channel and 1 for the selected one. ex: 4 channel, secect the third==> 0010) [default 1]");
TEST_PRINT(" --sample-rate-in=XXXX Input signal sample rate (default 48000)");
TEST_PRINT(" --out=zzz.raw output file"); TEST_PRINT(" --out=zzz.raw output file");
TEST_PRINT(" --format=xxx file Format : i16/float (default i16)");
TEST_PRINT(" --performance Generate signal to force algo to maximum process time"); TEST_PRINT(" --performance Generate signal to force algo to maximum process time");
TEST_PRINT(" --perf Enable performence test (little slower but real performence test)"); TEST_PRINT(" --perf Enable performence test (little slower but real performence test)");
TEST_PRINT(" --test=XXXX some test availlable ..."); TEST_PRINT(" --test=XXXX some test availlable ...");
TEST_PRINT(" RESAMPLING Test resampling data 16 bit mode"); TEST_PRINT(" RESAMPLING Test resampling data 16 bit mode");
TEST_PRINT(" --sample-rate-in=XXXX Input signal sample rate (default 48000)");
TEST_PRINT(" --sample-rate-out=XXXX Output signal sample rate (default 48000)"); TEST_PRINT(" --sample-rate-out=XXXX Output signal sample rate (default 48000)");
TEST_PRINT(" --quality=XX Resampling quality [0..10] (default 4)"); TEST_PRINT(" --quality=XX Resampling quality [0..10] (default 4)");
TEST_PRINT(" --nb=XX Number of channel in the file (default 1)"); TEST_PRINT(" --nb=XX Number of channel in the file (default 1)");
TEST_PRINT(" AEC Test AEC (SPEEX AEC is in 16 bits)");
TEST_PRINT(" --fb=XXXX.raw Input Feedback file");
TEST_PRINT(" --fb-filter=xxx Select the chanel desired in the input stream (same as --in-filter)");
TEST_PRINT(" --fb-delay=xxx dalay in sample in the signal feedback (default 0)");
TEST_PRINT(" --in-delay=xxx dalay in sample in the signal input (default 0)");
TEST_PRINT(" example: ");
TEST_PRINT(" ./XXX --test=AEC --fb=aaa_input.wav --in=aaa_input.wav --in-sample-rate=16000 --fb-filter=01 --in-filter=10 --format=i16 --in-delay=64");
exit(0); exit(0);
} else {
TEST_CRITICAL("unknow parameter : '" << data << "'");
} }
} }
// PERFORMANCE test only .... // PERFORMANCE test only ....
@ -368,15 +229,15 @@ int main(int _argc, const char** _argv) {
} }
if (test == "RESAMPLING") { if (test == "RESAMPLING") {
TEST_INFO("Start resampling test ... "); TEST_INFO("Start resampling test ... ");
if (inputName.isEmpty() == true) { if (inputName == "") {
TEST_ERROR("Can not Process missing parameters..."); TEST_ERROR("Can not Process missing parameters...");
exit(-1); exit(-1);
} }
TEST_INFO("Read input:"); TEST_INFO("Read input:");
etk::Vector<int16_t> inputData = loadDataI16(inputName, inputNumberChannel, inputSelectChannel, formatFileInteger16, inputSampleDelay); std::vector<int16_t> inputData = etk::FSNodeReadAllDataType<int16_t>(inputName);
TEST_INFO(" " << inputData.size() << " samples"); TEST_INFO(" " << inputData.size() << " samples");
// resize output : // resize output :
etk::Vector<int16_t> output; std::vector<int16_t> output;
output.resize(inputData.size()*sampleRateOut/sampleRateIn+5000, 0); output.resize(inputData.size()*sampleRateOut/sampleRateIn+5000, 0);
// process in chunk of 256 samples // process in chunk of 256 samples
int32_t blockSize = 256*nbChan; int32_t blockSize = 256*nbChan;
@ -398,87 +259,23 @@ int main(int _argc, const char** _argv) {
algo.process(&output[outputPosition], availlableSize, &inputData[iii*blockSize], blockSize); algo.process(&output[outputPosition], availlableSize, &inputData[iii*blockSize], blockSize);
if (perf == true) { if (perf == true) {
perfo.toc(); perfo.toc();
ethread::sleepMilliSeconds(1); usleep(1000);
} }
outputPosition += availlableSize*nbChan; outputPosition += availlableSize*nbChan;
} }
if (perf == true) { if (perf == true) {
TEST_INFO("Performance Result: "); TEST_INFO("Performance Result: ");
TEST_INFO(" blockSize=" << blockSize << " sample"); TEST_INFO(" blockSize=" << blockSize << " sample");
TEST_INFO(" min=" << perfo.getMinProcessing()); TEST_INFO(" min=" << perfo.getMinProcessing().count() << " ns");
TEST_INFO(" max=" << perfo.getMaxProcessing()); TEST_INFO(" max=" << perfo.getMaxProcessing().count() << " ns");
TEST_INFO(" avg=" << perfo.getTotalTimeProcessing().get()/perfo.getTotalIteration() << " ns"); TEST_INFO(" avg=" << perfo.getTotalTimeProcessing().count()/perfo.getTotalIteration() << " ns");
TEST_INFO(" min=" << (float((perfo.getMinProcessing().get()*sampleRateIn)/blockSize)/1000000000.0)*100.0 << " %"); TEST_INFO(" min=" << (float((perfo.getMinProcessing().count()*sampleRateIn)/blockSize)/1000000000.0)*100.0 << " %");
TEST_INFO(" max=" << (float((perfo.getMaxProcessing().get()*sampleRateIn)/blockSize)/1000000000.0)*100.0 << " %"); TEST_INFO(" max=" << (float((perfo.getMaxProcessing().count()*sampleRateIn)/blockSize)/1000000000.0)*100.0 << " %");
TEST_INFO(" avg=" << (float(((perfo.getTotalTimeProcessing().get()/perfo.getTotalIteration())*sampleRateIn)/blockSize)/1000000000.0)*100.0 << " %"); TEST_INFO(" avg=" << (float(((perfo.getTotalTimeProcessing().count()/perfo.getTotalIteration())*sampleRateIn)/blockSize)/1000000000.0)*100.0 << " %");
}
etk::FSNodeWriteAllDataType<int16_t>(outputName, output);
} }
TEST_PRINT("Store in file : '" << outputName << "' size = " << output.size());
ememory::SharedPtr<etk::io::Interface> fileIO = etk::uri::get(outputName);
if (fileIO->open(etk::io::OpenMode::Write) == false) {
return -1;
}
fileIO->writeAll<int16_t>(output);
fileIO->close();
///////////////////////////////////////////////////////////////////////////////////////////////////////////
} else if (test == "AEC") {
// process in chunk of XXX samples represent 10 ms of DATA ==> this is webRTC ...
int32_t blockSize = 32;
etk::Vector<int16_t> inputData = loadDataI16(inputName, inputNumberChannel, inputSelectChannel, formatFileInteger16, inputSampleDelay);
etk::Vector<int16_t> feedbackData = loadDataI16(feedbackName, feedbackNumberChannel, feedbackSelectChannel, formatFileInteger16, feedbackSampleDelay);
//etk::FSNodeWriteAllDataType<int16_t>("bbb_input_I16_1c.raw", inputData);
//etk::FSNodeWriteAllDataType<int16_t>("bbb_feedback_I16_1c.raw", feedbackData);
// resize output :
etk::Vector<int16_t> output;
output.resize(inputData.size(), 0);
Performance perfo;
{
audio::algo::speex::Aec algo;
algo.init(1, sampleRateIn, audio::format_int16);
blockSize = algo.getOptimalFrameSize();
int32_t lastPourcent = -1;
for (int32_t iii=0; iii<output.size()/blockSize; ++iii) {
if (lastPourcent != 100*iii / (output.size()/blockSize)) {
lastPourcent = 100*iii / (output.size()/blockSize);
TEST_INFO("Process : " << iii*blockSize << "/" << int32_t(output.size()/blockSize)*blockSize << " " << lastPourcent << "/100");
} else {
TEST_VERBOSE("Process : " << iii*blockSize << "/" << int32_t(output.size()/blockSize)*blockSize);
}
perfo.tic();
algo.process(&output[iii*blockSize], &inputData[iii*blockSize], &feedbackData[iii*blockSize], blockSize);
if (perf == true) {
perfo.toc();
ethread::sleepMilliSeconds(1);
}
}
}
TEST_PRINT("Process done");
if (perf == true) {
TEST_PRINT("Performance Result: ");
TEST_INFO(" blockSize=" << blockSize << " sample");
TEST_INFO(" min < avg < max =" << perfo.getMinProcessing().get() << "ns < "
<< perfo.getTotalTimeProcessing().get()/perfo.getTotalIteration() << "ns < "
<< perfo.getMaxProcessing().get() << "ns ");
float avg = (float(((perfo.getTotalTimeProcessing().get()/perfo.getTotalIteration())*sampleRateIn)/double(blockSize))/1000000000.0)*100.0;
TEST_INFO(" min < avg < max= " << (float((perfo.getMinProcessing().get()*sampleRateIn)/double(blockSize))/1000000000.0)*100.0 << "% < "
<< avg << "% < "
<< (float((perfo.getMaxProcessing().get()*sampleRateIn)/double(blockSize))/1000000000.0)*100.0 << "%");
TEST_PRINT("float : " << sampleRateIn << " : " << avg << "%");
}
TEST_PRINT("Store in file : '" << outputName << "' size = " << output.size());
ememory::SharedPtr<etk::io::Interface> fileIO = etk::uri::get(outputName);
if (fileIO->open(etk::io::OpenMode::Write) == false) {
return -1;
}
fileIO->writeAll<int16_t>(output);
fileIO->close();
}
TEST_PRINT(" ***************************************");
TEST_PRINT(" ** APPLICATION FINISHED OK **");
TEST_PRINT(" ***************************************");
return 0;
} }

2
version.txt
View File

@ -1 +1 @@
1.0.0 0.1.1