Timeshrinking
From SpeechWiki
(Difference between revisions)
Line 41: | Line 41: | ||
* Test svitchboard with fisher-trained model to see if we still get good results | * Test svitchboard with fisher-trained model to see if we still get good results | ||
* Train and test on plp+mlp, like svitchboard timeshrinking was done. | * Train and test on plp+mlp, like svitchboard timeshrinking was done. | ||
- | * Do baseline train+test to see if something changed in going from baseline to timeshrink structure files. | + | * Do baseline train+test to see if something changed in going from baseline to timeshrink structure files. (done, helped) |
+ | |||
+ | ==LM penalty and scale== | ||
+ | Since we now have 62 PLP+MLP features instead of 39 PLP, we should probably change LM scale by a factor 62/39=1.58. The original (not carefully tuned)PLP LM scale was 10. Perhaps it would make sense to multiply the LM penalty (-1 for PLP) by the same 1.58 factor. | ||
==Future Directions== | ==Future Directions== | ||
* Can be viewed as a two-mode special case of best-first viterbi search. So make a real best-first lattice search. Mark mentioned some attempts in the 80'ies to do this. | * Can be viewed as a two-mode special case of best-first viterbi search. So make a real best-first lattice search. Mark mentioned some attempts in the 80'ies to do this. | ||
[[Category:Fisher Experiments]] | [[Category:Fisher Experiments]] |
Revision as of 06:31, 8 October 2009
Contents |
Fisher experiments
<math>\tau</math> | frames dropped |
---|---|
1 | 0% |
.9 | ~5% |
.6 | ~35% |
train <math>\tau</math> | test <math>\tau</math> | dev 2000 utt WER | dev 2000 utt on triphone single-gaussian model WER | comments |
---|---|---|---|---|
1 | 1 | 51.6% | old baseline | |
1 | 1 | 53.7% | 78.2% | baseline rerun exactly as timeshrinking to really make sure it's not getting an unfair advantage |
.6 | .6 | 69.3% | ||
.9 | .9 | 56.3% | 80.4% | |
1 | .9 | 53.9% | ||
.9 | .9 | 57.2 | 80.7% | using the non-timeshrinking str file for test |
.9 | 1 | 54.6 | ||
1 | 1 | TR | 72.8% | PLP+MLP tandem |
.9 | .9 | TR | 73.1% | PLP+MLP tandem |