Speech recognition Coding

回答(8 个)

Raviteja
Raviteja 2011-2-4

3 个投票

First you need fundamentals of speech processing. Witch includes speech signal basic sounds and features. DSP techniques like, FFT, Windowing,STFT.
Some basic signal processing tasks like finding energy, spectrum of speech, autocorrelation, zero crossing detection, silence speech removal techniques etc. Then feature extraction from speech signals.
Feature extraction (LPC,MFCC). Then classification process of feature vectros by VQ.
Then statistical modelling like HMM, GMM.
You need to go following books "Digital processing of speech signals" by Rabinar "Fundamentals of speech recognition" by Rabinar And good books for DSP.
Mostly you read IEEE papers.
Is your goal to have speech recognition running in MATLAB, or to actually learn how to implement the algorithm?
If you just want to be able to use speech recognition in MATLAB, and you are running on Windows, you can pretty easily just incorporate the existing Windows capabilities using the MATLAB interface to .NET.
Here's some code my friend Jiro happened to pass around just the other day for this exact task. (Paste into a file in the editor and save).
function rec = speechrecognition
% Add assembly
NET.addAssembly('System.Speech');
% Construct engine
rec = System.Speech.Recognition.SpeechRecognitionEngine;
rec.SetInputToDefaultAudioDevice;
rec.LoadGrammar(System.Speech.Recognition.DictationGrammar);
% Define listener callback
addlistener(rec, 'SpeechRecognized', @recognizedFcn);
% Start recognition
rec.RecognizeAsync(System.Speech.Recognition.RecognizeMode.Multiple);
% Callback
function recognizedFcn(obj, e)
% Get text
txt = char(e.Result.Text);
% Split into words
w = regexp(txt, '\s', 'split');
if length(w) > 1
% Look for the occurrence of the phrase "search for"
idx = find(strcmp(w(1:end-1), 'search') & ...
strcmp(w(2:end), 'for'), 1, 'first');
if ~isempty(idx) && length(w) >= idx+2
% The words after are the search terms
searchTerm = sprintf('%s+', w{idx+2:end});
searchTerm(end) = '';
% Search on the web
web(['http://www.google.com/search?q=', searchTerm]);
fprintf(2, 'search for "%s"\n', strrep(searchTerm, '+', ' '));
else
%disp(txt)
end
elseif length(w) == 1 && strcmpi(w{1}, 'stop')
obj.RecognizeAsyncStop;
obj.delete;
%disp(txt);
disp('Stopping Speech Recognition. Thank you for using!');
else
%disp(txt);
end

3 个评论

Hello. Do you know on which version of OS and .NET whas this code written? I have this error using Jiro's code:
Error using ==> speechrecognition at 8
Message: Cannot find the requested data item, such as a data key or value.
Source: System.Speech
HelpLink:
Running on windows 7, .NET Framework 4
Thanks for your time.
B.Š.
Hello I'm working on a project that involves using speech recognition. Now I tried to use your code but I am not sure on the actual process in which to have the code actually work. Do you mind explain?
Some operational example code that uses this approach would be vey useful!

请先登录,再进行评论。

Nada Gamal
Nada Gamal 2011-4-20

0 个投票

Hi Raviteja , I made all steps of speech recognition except of classification because i used Elcudien Distance and calculate the minium distance to the templates .And i have a problem now in how can i implement Hidden Markove model in speech recognition . i don't understand this algrothim . Thanks a lot :) Best Regards, Nada Gamal
veni
veni 2016-8-24

0 个投票

how to write the speech recognisation in matlab coding? how to record the speech in matlab?
Neha Tonpe
Neha Tonpe 2022-11-25
编辑:Walter Roberson 2022-11-25
function rec = speechrecognition
% Add assembly
NET.addAssembly('System.Speech');
% Construct engine
rec = System.Speech.Recognition.SpeechRecognitionEngine;
rec.SetInputToDefaultAudioDevice;
rec.LoadGrammar(System.Speech.Recognition.DictationGrammar);
% Define listener callback
addlistener(rec, 'SpeechRecognized', @recognizedFcn);
% Start recognition
rec.RecognizeAsync(System.Speech.Recognition.RecognizeMode.Multiple);
% Callback
function recognizedFcn(obj, e)
% Get text
txt = char(e.Result.Text);
% Split into words
w = regexp(txt, '\s', 'split');
if length(w) > 1
% Look for the occurrence of the phrase "search for"
idx = find(strcmp(w(1:end-1), 'search') & ...
strcmp(w(2:end), 'for'), 1, 'first');
if ~isempty(idx) && length(w) >= idx+2
% The words after are the search terms
searchTerm = sprintf('%s+', w{idx+2:end});
searchTerm(end) = '';
% Search on the web
web(['http://www.google.com/search?q=', searchTerm]);
fprintf(2, 'search for "%s"\n', strrep(searchTerm, '+', ' '));
else
%disp(txt)
end
elseif length(w) == 1 && strcmpi(w{1}, 'stop')
obj.RecognizeAsyncStop;
obj.delete;
%disp(txt);
disp('Stopping Speech Recognition. Thank you for using!');
else
%disp(txt);
end
function rec = speechrecognition
% Add assembly
NET.addAssembly('System.Speech');
% Construct engine
rec = System.Speech.Recognition.SpeechRecognitionEngine;
rec.SetInputToDefaultAudioDevice;
rec.LoadGrammar(System.Speech.Recognition.DictationGrammar);
% Define listener callback
addlistener(rec, 'SpeechRecognized', @recognizedFcn);
% Start recognition
rec.RecognizeAsync(System.Speech.Recognition.RecognizeMode.Multiple);
% Callback
function recognizedFcn(obj, e)
% Get text
txt = char(e.Result.Text);
% Split into words
w = regexp(txt, '\s', 'split');
if length(w) > 1
% Look for the occurrence of the phrase "search for"
idx = find(strcmp(w(1:end-1), 'search') & ...
strcmp(w(2:end), 'for'), 1, 'first');
if ~isempty(idx) && length(w) >= idx+2
% The words after are the search terms
searchTerm = sprintf('%s+', w{idx+2:end});
searchTerm(end) = '';
% Search on the web
web(['http://www.google.com/search?q=', searchTerm]);
fprintf(2, 'search for "%s"\n', strrep(searchTerm, '+', ' '));
else
%disp(txt)
end
elseif length(w) == 1 && strcmpi(w{1}, 'stop')
obj.RecognizeAsyncStop;
obj.delete;
%disp(txt);
disp('Stopping Speech Recognition. Thank you for using!');
else
%disp(txt);
end
pathakunta
pathakunta 2024-1-26

0 个投票

First you need fundamentals of speech processing. Witch includes speech signal basic sounds and features. DSP techniques like, FFT, Windowing,STFT. Some basic signal processing tasks like finding energy, spectrum of speech, autocorrelation, zero crossing detection, silence speech removal techniques etc. Then feature extraction from speech signals. Feature extraction (LPC,MFCC). Then classification process of feature vectros by VQ. Then statistical modelling like HMM, GMM. You need to go following books "Digital processing of speech signals" by Rabinar "Fundamentals of speech recognition" by Rabinar And good books for DSP. Mostly you read IEEE papers.
Praveen
Praveen 2024-10-8

0 个投票

function rec = speechrecognition
% Add assembly
NET.addAssembly('System.Speech');
% Construct engine
rec = System.Speech.Recognition.SpeechRecognitionEngine;
rec.SetInputToDefaultAudioDevice;
rec.LoadGrammar(System.Speech.Recognition.DictationGrammar);
% Define listener callback
addlistener(rec, 'SpeechRecognized', @recognizedFcn);
% Start recognition
rec.RecognizeAsync(System.Speech.Recognition.RecognizeMode.Multiple);
% Callback
function recognizedFcn(obj, e)
% Get text
txt = char(e.Result.Text);
% Split into words
w = regexp(txt, '\s', 'split');
if length(w) > 1
% Look for the occurrence of the phrase "search for"
idx = find(strcmp(w(1:end-1), 'search') & ...
strcmp(w(2:end), 'for'), 1, 'first');
if ~isempty(idx) && length(w) >= idx+2
% The words after are the search terms
searchTerm = sprintf('%s+', w{idx+2:end});
searchTerm(end) = '';
% Search on the web
web(['http://www.google.com/search?q=', searchTerm]);
fprintf(2, 'search for "%s"\n', strrep(searchTerm, '+', ' '));
else
%disp(txt)
end
elseif length(w) == 1 && strcmpi(w{1}, 'stop')
obj.RecognizeAsyncStop;
obj.delete;
%disp(txt);
disp('Stopping Speech Recognition. Thank you for using!');
else
%disp(txt);
end

提问:

2011-2-4

回答:

2024-10-8

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by