:Units Paper
From SpeechWiki
(Difference between revisions)
(→Tests for units paper) |
|||
| Line 67: | Line 67: | ||
| || || || || || || || | | || || || || || || || | ||
|- | |- | ||
| - | |64 || 48 || 137 || 1061 || 67617 || [http://mickey.ifp.uiuc.edu/speech/akantor/fisher/exp/triphone/test2kUttOnConvGaus.noUnits/config73/LATEST.log 51.6%] || || baseline | + | |64 || 48 || 137 || 1061 || 67617 || [http://mickey.ifp.uiuc.edu/speech/akantor/fisher/exp/triphone/test2kUttOnConvGaus.noUnits/config73/LATEST.log 51.6%] || || baseline. The only difference to the above 50.6% is we are using 21% of Fisher instead of 80%. As a result the DTs also differ, but no other parmeters were changed. |
|- | |- | ||
|128 || 48 || 137 || 1061 || 134139 || [http://mickey.ifp.uiuc.edu/speech/akantor/fisher/exp/triphone/test2kUtt/convGaus.noUnits/unit.tri.128gau/LATEST.log 49.3%] || || baseline, 128 gaussians, 2.3% WER improvment over 64 | |128 || 48 || 137 || 1061 || 134139 || [http://mickey.ifp.uiuc.edu/speech/akantor/fisher/exp/triphone/test2kUtt/convGaus.noUnits/unit.tri.128gau/LATEST.log 49.3%] || || baseline, 128 gaussians, 2.3% WER improvment over 64 | ||
Latest revision as of 23:01, 16 July 2010
Contents |
Outline
- Intro
- Unit Selection
- Mistake instance
- Unit
- Replacement
- Multwords
- Baseline Description
- Vocab: single most frequent pronunciation from a multi-pronunciation dictionary (better than multi-pronunciation)
- Results
- what to emphasize? Ideally, units+DTs will beat just DTs for every number of components. Even if we cannot grow the components until improvement bottoms out, at least there will be a trend.
- Conclusion
- Future work: consider context during unit selection (right now the unit is context-free - the same unit appearing in all contexts where replacements took place).
Tests for units paper
| compPer: | units: | monophone states | Mix: | totalComp: | WER | Test WER | Important |
|---|---|---|---|---|---|---|---|
| 512 | 1 | 503 | 256k | TR | |||
| 256 | 1 | 1000 | 256k | TR | |||
| 64 | 1 | 3854 | 256k | 49.3 | |||
| 64 | 2 | 2000 | 256k | ? | |||
| 32 | 4 | 2000 | 256k | ? | |||
| 32 | 2 | 4000 | 256k | ? | |||
| alternatively | |||||||
| 256 | 48 | 137 | 503 | 127971 | 53.0 | ||
| 128 | 48 | 137 | 1033 | 131185 | 50.9 | ||
| 32 | 48 | 137 | 3845 | 122907 | 51.4 | ||
| 64 | 112 | 615 | 2024 | ~128k | TR | ||
| 16 | 4 | 2000 | 128k | ? | |||
| 16 | 112 | 615 | 4000 | 128k | ? | ||
| my best clean baseline so far: | |||||||
| 64 | 48 | 137 | 1033 | 65900 | 50.3% | ||
| 64 | 48 | 137 | 1037 | 65900 | 50.6% | Finally, multi-unit with no units gives the same WER | |
| from here onwards, we use only one quarter of the traing data to save time: | |||||||
| 64 | 48 | 137 | 1061 | 67617 | 51.6% | baseline. The only difference to the above 50.6% is we are using 21% of Fisher instead of 80%. As a result the DTs also differ, but no other parmeters were changed. | |
| 128 | 48 | 137 | 1061 | 134139 | 49.3% | baseline, 128 gaussians, 2.3% WER improvment over 64 | |
| 256 | 48 | 137 | 1061 | 251078 | 47.8% | baseline, 256 gaussians, 1.5 WER improvement over 128 | |
| 64 | 117 | 635 | 1604 | 102321 | 49.8% | word-internal units, no tying among units | |
| 128 | 117 | 635 | 1604 | 202851 | 47.8% | word-internal units, no tying among units | |
| 64 | 115 | 635 | 1963 | 124746 | 50.0% | word-internal units, fullly tied units |
put in above table
Debuging
A number of bugs have been fixed, and results on the SST:Units Paper Debugging are hopefully no longer relevant.
Monophone tests
Finally, at least something reasonable: and (hopefully) a 2% WER improvement in the baseline So redoing monophone tests:
| trainConfig | testConfig | Descr | States | WER | WER 2k | Comments |
|---|---|---|---|---|---|---|
| triUnitsModel/config28 | testc67triUnitsModelc28/config67 | baseline but using the new testing stuff: --maxStates 0 --unitType wordInternalOnly --subUnits asBefore --growUnitSet 0 | 137 | 84.3% | 86.0% | |
| moreDTsModel/config20 | trTestTrigramFixed/config19 | baseline | 137 | 84.3% | Same as above but using older code | |
| triUnitsModel/config27 | testc67TriOnBreakdownModelc27/config67 | --maxStates 500 --unitType wordInternalOnly --subUnits asBefore --growUnitSet 0 | 627 | 87.2 | 87.6 | |
| triUnitsModel/config26 | testc67TriOnBreakdownModelc26/config67 | --maxStates 500 --unitType wordInternalOnly --subUnits asBefore | 627 | 87.1 was 91.1% | TE | |
| triUnitsModel/config25 | xx | --maxStates 500 --unitType wordInternalOnly | 636 | xx | 87.1 | |
| triUnitsModel/config24 | xx | --maxStates 500 | 615 | xx | xx | |
| triUnitsModel/config29 | xx | --maxStates 500 --unitType multiWordOnly | 637 | xx | 88.2 | There must be something wrong with this - the confusion pairs are not making sense and there are way too many deletions |
| triUnitsModel/config30 | xx | --maxStates 500 --unitType wordInternalOnly --subUnits asBefore, initializeUnitsFromFile | 627 | xx | 86.0 | |
| triUnitsModel/config31 | xx | --maxStates 500 --contextType wordInternalOnly --subUnits asBefore --tieContext none | 633 | xx | 85.8 | finally a slight improvement. |
