Speech recognition Coding

370 views (last 30 days)
Shubham
Shubham on 4 Feb 2011
Commented: Steven Dakin on 10 Jan 2021
somebody please tell me how do i go about speech recognition coding.

Answers (4)

Raviteja
Raviteja on 4 Feb 2011
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.

Michelle Hirsch
Michelle Hirsch on 4 Feb 2011
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 Comments
Steven Dakin
Steven Dakin on 10 Jan 2021
Some operational example code that uses this approach would be vey useful!

Sign in to comment.


Nada Gamal
Nada Gamal on 20 Apr 2011
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 on 24 Aug 2016
how to write the speech recognisation in matlab coding? how to record the speech in matlab?

Community Treasure Hunt

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

Start Hunting!