Timeshrinking
From SpeechWiki
(Difference between revisions)
| Line 19: | Line 19: | ||
|- | |- | ||
| 1 || 1 || [{{FisherPath}}/exp/timeshrink/test/unit.tri.timeshrink.1/LATEST.log 53.7%] || [{{FisherPath}}/exp/timeshrink/test/triphoneSingleGausian/unit.tri.timeshrink.1.onSingleGaussian/LATEST.log 78.2%] || baseline rerun exactly as timeshrinking to really make sure it's not getting an unfair advantage | | 1 || 1 || [{{FisherPath}}/exp/timeshrink/test/unit.tri.timeshrink.1/LATEST.log 53.7%] || [{{FisherPath}}/exp/timeshrink/test/triphoneSingleGausian/unit.tri.timeshrink.1.onSingleGaussian/LATEST.log 78.2%] || baseline rerun exactly as timeshrinking to really make sure it's not getting an unfair advantage | ||
| + | |- | ||
| + | | 1 || 1 || [{{FisherPath}}/exp/timeshrink/test/unit.tri.timeshrink.1/LATEST.log 54.5%] || || baseline rerun exactly as timeshrinking LM_scale 16 to double check it's tuned. Should be worse, and it is. | ||
|- | |- | ||
| .6 || .6 || 69.3% | | .6 || .6 || 69.3% | ||
| Line 34: | Line 36: | ||
| 1 || 1 || [{{FisherPath}}/exp/timeshrink/test/unit.tri.timeshrink.1.mlp.lmAdj/LATEST.log 50.6%] || || PLP+MLP tandem, LM scale 16 | | 1 || 1 || [{{FisherPath}}/exp/timeshrink/test/unit.tri.timeshrink.1.mlp.lmAdj/LATEST.log 50.6%] || || PLP+MLP tandem, LM scale 16 | ||
|- | |- | ||
| - | | .9 || .9 || [{{FisherPath}}/exp/timeshrink/test/.../LATEST.log | + | | 1 || 1 || [{{FisherPath}}/exp/timeshrink/test/unit.tri.timeshrink.1.mlp.lmSc20/LATEST.log 49.7%] || || PLP+MLP tandem, LM scale 20 |
| + | |- | ||
| + | | 1 || 1 || [{{FisherPath}}/exp/timeshrink/test/unit.tri.timeshrink.1.mlp.lmSc25/LATEST.log 50.0%] || || PLP+MLP tandem, LM scale 25 | ||
| + | |- | ||
| + | | .9 || .9 || [{{FisherPath}}/exp/timeshrink/test/triphoneSingleGausian/unit.tri.timeshrink.point9.mlp.lmSc16/LATEST.log 49.9% ] || || PLP+MLP tandem lm_scale 16 | ||
| + | |- | ||
| + | | .9 || .9 || [{{FisherPath}}/exp/timeshrink/test/triphoneSingleGausian/unit.tri.timeshrink.point9.mlp.lmSc20/LATEST.log 49.3% ] || || PLP+MLP tandem lm_scale 20 | ||
| + | |- | ||
| + | |||
|-|} | |-|} | ||
| Line 42: | Line 52: | ||
* 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 (done, improved baseline and test by 5% WER!). |
* Do baseline train+test to see if something changed in going from baseline to timeshrink structure files. (done, helped) | * Do baseline train+test to see if something changed in going from baseline to timeshrink structure files. (done, helped) | ||
| Line 50: | Line 60: | ||
==final test== | ==final test== | ||
20k utterances, at tau=.9, 6.02% of the frames are dropped, 158839 segments and 3.5 frames per segment. | 20k utterances, at tau=.9, 6.02% of the frames are dropped, 158839 segments and 3.5 frames per segment. | ||
| + | |||
| + | lm_scale was roughly tuned on the baseline, and the same one was used on the test, although tuning for the test would help because there are %5 fewer frames per word on average. | ||
| + | |||
| + | {| class="wikitable" | ||
| + | |+ Final test Timeshrinking results on fisher | ||
| + | ! <math>\tau</math> !! test 20k utt WER !! comments | ||
| + | |- | ||
| + | | 1 || [{{FisherPath}}/exp/timeshrink/test/unit.tri.timeshrink.1.mlp.lmSc20.final/LATEST.log TE] || PLP+MLP tandem, LM scale 20 (tuned) | ||
| + | |- | ||
| + | | .9 || [{{FisherPath}}/exp/timeshrink/test/unit.tri.timeshrink.point9.mlp.lmSc20.final/LATEST.log TE] || everything except <math>\tau</math> is same as baseline. | ||
| + | |-|} | ||
| + | |||
==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 23:54, 11 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 |
| 1 | 1 | 54.5% | baseline rerun exactly as timeshrinking LM_scale 16 to double check it's tuned. Should be worse, and it is. | |
| .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 | 55.4% | 72.8% | PLP+MLP tandem |
| 1 | 1 | 50.6% | PLP+MLP tandem, LM scale 16 | |
| 1 | 1 | 49.7% | PLP+MLP tandem, LM scale 20 | |
| 1 | 1 | 50.0% | PLP+MLP tandem, LM scale 25 | |
| .9 | .9 | 49.9% | PLP+MLP tandem lm_scale 16 | |
| .9 | .9 | 49.3% | PLP+MLP tandem lm_scale 20 |
| <math>\tau</math> | test 20k utt WER | comments |
|---|---|---|
| 1 | TE | PLP+MLP tandem, LM scale 20 (tuned) |
| .9 | TE | everything except <math>\tau</math> is same as baseline. |
