Title | ||
---|---|---|
Enhanced tree clustering with single pronunciation dictionary for conversational speech recognition |
Abstract | ||
---|---|---|
Modeling pronunciation variation is key for recogniz- ing conversational speech. Rather than being limited to dictionary modeling, we argue that triphone clustering is an integral part of pronunciation modeling. We propose a new approach called enhanced tree clustering .T his approach, in contrast to traditional decision tree based state tying, allows parameter sharing across phonemes. We show that accurate pronunciation modeling can be achieved through efficient parameter sharing in the acous- tic model. Combined with a single pronunciation dic- tionary, a 1.8% absolute word error rate improvement is achieved on Switchboard, a large vocabulary conversa- tional speech recognition task. |
Year | Venue | Keywords |
---|---|---|
2003 | INTERSPEECH | speech recognition,decision tree,word error rate |
Field | DocType | Citations |
Triphone,Pronunciation,Decision tree,Pattern recognition,Computer science,Word error rate,Speech recognition,Artificial intelligence,Natural language processing,Cluster analysis,Vocabulary,Acoustic model | Conference | 10 |
PageRank | References | Authors |
1.25 | 5 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hua Yu | 1 | 20 | 2.74 |
T. Schultz | 2 | 2423 | 252.72 |