Quick mentor note: We are converting to daily progress reports which I will combine into draft blog posts that the students will proofread, copy-edit, and approve for publication. This will help keep all three of us on schedule. Sorry I am behind. The good news is that both students made it from "on schedule" to "ahead of schedule" in a sprint for the evaluations.
Congratulations, Troy and Ronanki!
Please post your daily-ish (4 or more per week) progress reports here. Thanks!
I somehow forgot this...let me start from today onwards...!!
ReplyDeleteDate: 19/07/2012
ReplyDeleteStudied about Power Normalized Cepstral Coefficients (PNCC) which are more robust towards speech recognition even in noisy environment. PNCC are 13 in dimension, computationally more cost than MFCC but performs better than MFCC in speech recognition. Got the code, able to run it. Will Compare accuracy on TIMIT database tomorrow !!
Date: 22/07/2012
ReplyDeleteStill doing with random phrase pronunciation evaluation @ http://talknicer.net/~ronanki/test/random.html and testing PNCC on TIMIT database !!
Date: 23/07/2012
ReplyDeleteTIMIT statistics are ready !!
Total 6300 utterances @ 10 utterances from each speaker (Total:630 speakers)
Successfully aligned files: 6149 out of 6300
and statistics are derived from those 6149 aligned files:
http://talknicer.net/~ronanki/phrase_data/statistics/TIMIT_statistics.txt
Position: 0/1/2 -> begin/middle/end
Count : Represents number of times each phone occurred
This comment has been removed by the author.
ReplyDeleteDate: 25/07/2012
ReplyDeleteI completed the random phrase pronunciation evaluation system and is in testing phase @ http://talknicer.net/~ronanki/test/
Date: 29/07/2012
ReplyDeleteCompleted extracting mfcc, pncc, phonological features