speech to text

39 views (last 30 days)
Dhaval Gondaliya
Dhaval Gondaliya on 20 Mar 2012
Edited: Adam Danz on 13 Dec 2019
I am doing a project on the speech recognition for home automation but i can not find the code to convert the speech into the text and also i can not justify that what is spoken in the speech? so please any one can help me?
I have some code to distinguish the speech but it does not work for different speeches.
If you have that code then please send me .
My email id :dhavalgondaliya55@gmail.com.
  3 Comments
Walter Roberson
Walter Roberson on 4 Sep 2012
Please be more specific about the difficulty you are encountering.
Adam Danz
Adam Danz on 13 Dec 2019
Edited: Adam Danz on 13 Dec 2019
Several comments have been removed where users were merely leaving their personal email addresses asking for code.
See Gabriele Bunkheila's answer below for source code.

Sign in to comment.

Accepted Answer

Image Analyst
Image Analyst on 20 Mar 2012
  3 Comments
PK
PK on 23 Jan 2013
Hi Image analyst I have seen these links but in the second link can you tell me how exactly to work with code.
Walter Roberson
Walter Roberson on 23 Jan 2013
The company sells the source code for about Eur 30.
I would not think it especially likely that Image Analyst has paid the company for the source to a speech project... not his line of work.

Sign in to comment.

More Answers (1)

Gabriele Bunkheila
Gabriele Bunkheila on 16 Jan 2018
Edited: Gabriele Bunkheila on 6 Mar 2018
Hi Dhaval,
I work at MathWorks and I noticed this old enquiry of yours just now. This is probably not directly relevant to your original question, but I thought I'd leave a link to our recent MATLAB Central sumbission speech2text in case it was useful to others:
That leverages 3rd party speech-to-text web services (so far including from Google, Microsoft and IBM) calling their web API directly from MATLAB via a simple MATLAB Function. This may turn in handy to test the performance of your own solution using well-established services.
The syntax looks like the following:
>> [samples, fs] = audioread('helloaudioPD.wav');
>> soundsc(samples, fs)
>> speechObject = speechClient('Google','languageCode','en-US');
>> outInfo = speech2text(speechObject, samples, fs);
>> outInfo.TRANSCRIPT
ans =
'hello audio product Developers'
>> outInfo.CONFIDENCE
ans =
0.9385
Please refer to the html folder in the submission for a step-by-step getting started guide.
Thanks,
Gabriele.
  3 Comments
Gabriele Bunkheila
Gabriele Bunkheila on 7 Dec 2018
Hi Kavitha,
You can find altearnative sintax options (i.e. for IBM and Microsoft) at the following page in the online documentation:https://www.mathworks.com/help/audio/ug/speech2text.html
I hope this helps.
Regards,
Gabriele.
Henan Yu
Henan Yu on 6 Oct 2019
Hello Gabriele,
I am doing the Speech recognition project, and I followed the link you shared, but it turns out this error: 'unauthorized' voice. Here is my code:
[y,fs] = audioread('audio-file.flac');
soundsc(y, fs)
speechObject = speechClient('IBM','languageCode','en-US')
speechObjectIBM = speechClient('IBM','keywords',"example,keywords",'keywords_threshold',0.5);
speechObjectIBM.Options
outInfo = speech2text(speechObject,y,fs)
I am wondering is this because the code is not correct or there is something wrong with my .JSON file ?
Looking forward to hearing from you.
Thank you
Regards,
Henan

Sign in to comment.

Community Treasure Hunt

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

Start Hunting!