Timeshrinking
From SpeechWiki
(Difference between revisions)
(New page: ==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 ...) |
|||
Line 1: | Line 1: | ||
+ | ==Fisher experiments== | ||
+ | |||
+ | {| class="wikitable" | ||
+ | ! <math>\tau</math> !! dev 2k utt WER | ||
+ | |- | ||
+ | | .6 || 69.3% | ||
+ | |} | ||
+ | |||
+ | I have to check for bugs. It could be that the threshold is too low or it could be something else too. | ||
+ | |||
+ | |||
==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 08:07, 20 August 2009
Fisher experiments
<math>\tau</math> | dev 2k utt WER |
---|---|
.6 | 69.3% |
I have to check for bugs. It could be that the threshold is too low or it could be something else too.
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.