:Units Paper
From SpeechWiki
(Difference between revisions)
m |
m |
||
Line 41: | Line 41: | ||
|128 || 48 || 137 || 1033 || 131185 || [http://mickey.ifp.uiuc.edu/speech/akantor/fisher/exp/triphone/moreDTsTest/config13/test0/accuracy/out.nosil.trn.dtl 50.9] || || | |128 || 48 || 137 || 1033 || 131185 || [http://mickey.ifp.uiuc.edu/speech/akantor/fisher/exp/triphone/moreDTsTest/config13/test0/accuracy/out.nosil.trn.dtl 50.9] || || | ||
|- | |- | ||
- | |32 || 48 || 137 || | + | |32 || 48 || 137 || 3845 || 122907 || [http://mickey.ifp.uiuc.edu/speech/akantor/fisher/exp/triphone/moreDTsC21Test/config11/test0/accuracy/out.nosil.trn.dtl 51.4] || || |
|- | |- | ||
- | | | + | |64 || 112 || 615 || 2024 || ~128k || TR || || |
|- | |- | ||
|16 || 4 || || 2000 || 128k || ? || || | |16 || 4 || || 2000 || 128k || ? || || | ||
Line 52: | Line 52: | ||
+ | ==For Mark tomorrow== | ||
+ | * What is the story to tell with the above experiments? Do we need a clean replacement: 2000 leaf nodes through just DTs and also 2000 leaf nodes through DT+units? | ||
+ | |||
+ | * | ||
[[Category:Fisher Experiments]] | [[Category:Fisher Experiments]] |
Revision as of 03:42, 8 April 2009
Outline
- Intro
- Unit Selection
- Mistake instance
- Unit definition
- Replacement definition
- Multwords
- Baseline Description
- Vocab: single most frequent pronunciation from a multi-pronunciation dictionary (better than multi-pronunciation)
- Results
- Conclusion
- 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 | ? |
For Mark tomorrow
- What is the story to tell with the above experiments? Do we need a clean replacement: 2000 leaf nodes through just DTs and also 2000 leaf nodes through DT+units?