Original language | English |
---|
Pages (from-to) | 4-6 |
---|
Number of pages | 3 |
---|
Journal | IEEE Signal Processing Letters |
---|
Volume | 3 |
---|
Issue number | 1 |
---|
DOIs | |
---|
Publication status | Published - 1 Jan 1996 |
---|
Abstract:
Introduces a new pruning strategy for large vocabulary continuous speech recognition based on direct estimates of local posterior phone probabilities. This approach is well suited to hybrid connectionist/hidden Markov model systems. Experiments on the Wall Street Journal task using a 20000 word vocabulary and a trigram language model have demonstrated that phone deactivation pruning can increase the speed of recognition-time search by up to a factor of 10, with a relative increase in error rate of less than 2%.
ID: 37432014