# Language model and Acoustic Model Speech recognition development for Malayalam using CMU Sphinx **URL:** \ **Category:** GSoC\ **Created:** [March 24, 2016, 6:36am UTC](https://community.smc.org.in/t/language-model-and-acoustic-model-speech-recognition-development-for-malayalam-using-cmu-sphinx/33 "2016-03-24T06:36:47Z")\ **Posts on this page:** 10\ **Page:** 1
**Author:** ![IMSreenadh](https://community.smc.org.in/user_avatar/community.smc.org.in/imsreenadh/32/29_2.png) [@IMSreenadh](https://community.smc.org.in/u/IMSreenadh)\ **Post date:** [March 24, 2016, 6:36am UTC](https://community.smc.org.in/t/language-model-and-acoustic-model-speech-recognition-development-for-malayalam-using-cmu-sphinx/33/1 "2016-03-24T06:36:47Z")
Discussion thread for LM and AM development for Speech recognition of Malayalam uisng CMU Sphinx Mentor : Mrs. Deepa Gopinath Link to the current work I have done: [ml-lm-am](https://github.com/sreecodeslayer/ml%C2%ADam%C2%ADlm%C2%ADcmusphinx) The workflow I followed for my initial trial of the idea during my Major project: 1. Use The Datuk corpus as the source for Malayalam corpus ([http://olam.in/open/datuk/](http://olam.in/open/datuk/)) 2. Build a Phonetic dictionary using this corpus 3. Develop unigram, digram, and trigram Statistical language model using CMU­CSLM toolkit. 4. Training phase and acoustic model development using five different people. 5. Testing for accuracy, could only achieve roughly 60% due to time limitations for the project submission. Find the complete Proposal over [here](https://docs.google.com/document/d/1TRhb74gfb_K_Meob2YNJQM7wDgPV4V_yfTqTe9v0rJE/edit?usp=sharing) ---
**Author:** ![IMSreenadh](https://community.smc.org.in/user_avatar/community.smc.org.in/imsreenadh/32/29_2.png) [@IMSreenadh](https://community.smc.org.in/u/IMSreenadh)\ **Post date:** [May 27, 2016, 4:49am UTC](https://community.smc.org.in/t/language-model-and-acoustic-model-speech-recognition-development-for-malayalam-using-cmu-sphinx/33/2 "2016-05-27T04:49:29Z")
Blog update : [Here](https://medium.com/@imSreenadh/mentioning-the-huge-contributions-12005bcaad06#.wy7p8or2u) 😁 ---
**Author:** ![stultus](https://community.smc.org.in/user_avatar/community.smc.org.in/stultus/32/28_2.png) [@stultus](https://community.smc.org.in/u/stultus)\ **Post date:** [May 28, 2016, 7:50pm UTC](https://community.smc.org.in/t/language-model-and-acoustic-model-speech-recognition-development-for-malayalam-using-cmu-sphinx/33/3 "2016-05-28T19:50:38Z")
I will create a repo in gitlab under smc, please fork it and give PR’s regularly. what should be the name of the repo? ---
**Author:** ![IMSreenadh](https://community.smc.org.in/user_avatar/community.smc.org.in/imsreenadh/32/29_2.png) [@IMSreenadh](https://community.smc.org.in/u/IMSreenadh)\ **Post date:** [May 29, 2016, 6:58am UTC](https://community.smc.org.in/t/language-model-and-acoustic-model-speech-recognition-development-for-malayalam-using-cmu-sphinx/33/4 "2016-05-29T06:58:51Z")
That’s fine. How about naming it “samsaaram” ? ---
**Author:** ![IMSreenadh](https://community.smc.org.in/user_avatar/community.smc.org.in/imsreenadh/32/29_2.png) [@IMSreenadh](https://community.smc.org.in/u/IMSreenadh)\ **Post date:** [May 29, 2016, 11:24am UTC](https://community.smc.org.in/t/language-model-and-acoustic-model-speech-recognition-development-for-malayalam-using-cmu-sphinx/33/5 "2016-05-29T11:24:34Z")
**Blog Updates** 😋 [Follow me here](https://medium.com/@imSreenadh) for further updates and also you can read my blog updates from the past three weeks. ---
**Author:** ![stultus](https://community.smc.org.in/user_avatar/community.smc.org.in/stultus/32/28_2.png) [@stultus](https://community.smc.org.in/u/stultus)\ **Post date:** [May 30, 2016, 5:50am UTC](https://community.smc.org.in/t/language-model-and-acoustic-model-speech-recognition-development-for-malayalam-using-cmu-sphinx/33/6 "2016-05-30T05:50:41Z")
> How about naming it “samsaaram” ? I think a name that non-malayalees can recognize will be a better choice ---
**Author:** ![IMSreenadh](https://community.smc.org.in/user_avatar/community.smc.org.in/imsreenadh/32/29_2.png) [@IMSreenadh](https://community.smc.org.in/u/IMSreenadh)\ **Post date:** [May 30, 2016, 3:47pm UTC](https://community.smc.org.in/t/language-model-and-acoustic-model-speech-recognition-development-for-malayalam-using-cmu-sphinx/33/7 "2016-05-30T15:47:42Z")
Ohh… right! Well then normal naming like ‘ml-speech’ or something similar. Can’t get anything simple enough in my mind. 😃 One more doubt, Is it possible to edit the description? There is a mistake in the hyperlink I provided for ‘ml-lm-am’ . Its supposed to be this : [GitHub - sreecodeslayer/ml-am-lm-cmusphinx: This is Malayalam Speech Recognition model developed for CMUSphinx. This is now used for Google Summer Code 2016](https://github.com/sreecodeslayer/ml-am-lm-cmusphinx) ---
**Author:** ![IMSreenadh](https://community.smc.org.in/user_avatar/community.smc.org.in/imsreenadh/32/29_2.png) [@IMSreenadh](https://community.smc.org.in/u/IMSreenadh)\ **Post date:** [June 10, 2016, 12:57pm UTC](https://community.smc.org.in/t/language-model-and-acoustic-model-speech-recognition-development-for-malayalam-using-cmu-sphinx/33/8 "2016-06-10T12:57:57Z")
[Blog Update] ([Slow as a Snail. “by persistence the snail reached the… | by Sreenadh T C | Medium](https://medium.com/@imSreenadh/slow-as-a-snail-58c09b46ec32)) Am currently pushing my works to the previously mentioned repository on GitHub 🙂 😌 ---
**Author:** ![asd](https://community.smc.org.in/user_avatar/community.smc.org.in/asd/32/16_2.png) [@asd](https://community.smc.org.in/u/asd)\ **Post date:** [June 27, 2016, 4:24pm UTC](https://community.smc.org.in/t/language-model-and-acoustic-model-speech-recognition-development-for-malayalam-using-cmu-sphinx/33/9 "2016-06-27T16:24:34Z")
> [@IMSreenadh](#): > > Is it possible to edit the description? Yes, it is possible to edit discourse posts. Just find the edit button among the tools on the bottom of the post. ---
**Author:** ![IMSreenadh](https://community.smc.org.in/user_avatar/community.smc.org.in/imsreenadh/32/29_2.png) [@IMSreenadh](https://community.smc.org.in/u/IMSreenadh)\ **Post date:** [July 19, 2016, 2:28pm UTC](https://community.smc.org.in/t/language-model-and-acoustic-model-speech-recognition-development-for-malayalam-using-cmu-sphinx/33/10 "2016-07-19T14:28:20Z")
##Status update: Completed an initial build of Language Model and Acoustic Model. Need to test accuracy and see if I can improve a bit perhaps.