Documentation

This is machine translation

Translated by Microsoft
Mouseover text to see original. Click the button below to return to the English verison of the page.

Note: This page has been translated by MathWorks. Please click here
To view all translated materals including this page, select Japan from the country navigator on the bottom of this page.

G.729 Voice Activity Detection

This example shows how to implement the ITU-T G.729 Voice Activity Detector (VAD)

Introduction

Voice Activity Detection (VAD) is a critical problem in many speech/audio applications including speech coding, speech recognition or speech enhancement. For instance, the ITU-T G.729 standard uses VAD modules to reduce the transmission rate during silence periods of speech.

Algorithm

At the first stage, four parametric features are extracted from the input signal. These parameters are the full-band and low-band frame energies, the set of line spectral frequencies (LSF) and the frame zero crossing rate. If the frame number is less than 32, an initialization stage of the long-term averages takes place, and the voice activity decision is forced to 1 if the frame energy from the LPC analysis is above 21 dB. Otherwise, the voice activity decision is forced to 0. If the frame number is equal to 32, an initialization stage for the characteristic energies of the background noise occurs.

At the next stage, a set of difference parameters is calculated. This set is generated as a difference measure between the current frame parameters and running averages of the background noise characteristics. Four difference measures are calculated:

a) A spectral distortion
b) An energy difference
c) A low-band energy difference
d) A zero-crossing difference

The initial voice activity decision is made at the next stage, using multi-boundary decision regions in the space of the four difference measures. The active voice decision is given as the union of the decision regions and the non-active voice decision is its complementary logical decision. Energy considerations, together with neighboring past frames decisions, are used for decision smoothing. The running averages have to be updated only in the presence of background noise, and not in the presence of speech. An adaptive threshold is tested, and the update takes place only if the threshold criterion is met.

VAD Implementation

vadG729 is the function containing the algorithm's implementation.

Initialization

Set up an audio source. This example uses an audio file reader.

audioSource = dsp.AudioFileReader('SamplesPerFrame',80,...
                               'Filename','speech_dft_8kHz.wav',...
                               'OutputDataType', 'single');
% Note: You can use a microphone as a source instead by using an audio
% device reader (NOTE: audioDeviceReader requires an Audio System Toolbox
% (TM) license)
% audioSource = audioDeviceReader('OutputDataType', 'single', ...
%                              'NumChannels', 1, ...
%                              'SamplesPerFrame', 80, ...
%                              'SampleRate', 8000);
% Create a time scope to visualize the VAD decision (channel 1) and the
% speech data (channel 2)
scope = dsp.TimeScope(2, 'SampleRate', [8000/80 8000], ...
                      'BufferLength', 80000, ...
                      'YLimits', [-0.3 1.1], ...
                      'ShowGrid', true, ...
                      'Title','Decision speech and speech data', ...
                      'TimeSpanOverrunAction','Scroll');

Stream Processing Loop

% Initialize VAD parameters
VAD_cst_param = vadInitCstParams;
clear vadG729
% Run for 10 seconds
numTSteps = 1000;
while(numTSteps)
  % Retrieve 10 ms of speech data from the audio recorder
  speech = audioSource();
  % Call the VAD algorithm
  decision = vadG729(speech, VAD_cst_param);
  % Plot speech frame and decision: 1 for speech, 0 for silence
  scope(decision, speech);
  numTSteps = numTSteps - 1;
end
release(scope);

Cleanup

Close the audio input device and release resources

release(audioSource);

Generating and Using the MEX-File

MATLAB Coder can be used to generate C code for the function vadG729. In order to generate a MEX-file, execute the following command.

codegen vadG729 -args {single(zeros(80,1)), coder.Constant(VAD_cst_param)}

Speed Comparison

Creating MEX-Files often helps achieve faster run-times for simulations. The following lines of code first measure the time taken by the MATLAB function and then measure the time for the run of the corresponding MEX-file. Note that the speedup factor may be different for different machines.

audioSource = dsp.AudioFileReader('speech_dft_8kHz.wav', ...
                              'SamplesPerFrame', 80, ...
                              'OutputDataType', 'single');
clear vadG729
VAD_cst_param = vadInitCstParams;
tic;
while ~isDone(audioSource)
  speech = audioSource();
  decision = vadG729(speech, VAD_cst_param);
end
t1 = toc;

reset(audioSource);

tic;
while ~isDone(audioSource)
  speech = audioSource();
  decision = vadG729_mex(speech, VAD_cst_param);
end
t2 = toc;

disp('RESULTS:')
disp(['Time taken to run the MATLAB code: ', num2str(t1), ' seconds']);
disp(['Time taken to run the MEX-File: ', num2str(t2), ' seconds']);
disp(['Speed-up by a factor of ', num2str(t1/t2),...
    ' is achieved by creating the MEX-File']);
RESULTS:
Time taken to run the MATLAB code: 0.44421 seconds
Time taken to run the MEX-File: 0.074348 seconds
Speed-up by a factor of 5.9747 is achieved by creating the MEX-File

Reference

ITU-T Recommendation G.729 - Annex B: A silence compression scheme for G.729 optimized for terminals conforming to ITU-T Recommendation V.70

Was this topic helpful?