Abstract | ||
---|---|---|
This paper explores the use of continuous speech data to learn stochastic lexicons. Building on previous work in which we augmented graphones with acoustic examples of isolated words, we extend our pronunciation mixture model framework to two domains containing spontaneous speech: a weather information retrieval spoken dialogue system and the academic lectures domain. We find that our learned lexicons out-perform expert, hand-crafted lexicons in each domain. |
Year | Venue | Keywords |
---|---|---|
2011 | 12TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2011 (INTERSPEECH 2011), VOLS 1-5 | grapheme-to-phoneme conversion, pronunciation models, lexical representation |
Field | DocType | Citations |
Pronunciation,Computer science,Speech recognition,Natural language processing,Artificial intelligence,Mixture model | Conference | 3 |
PageRank | References | Authors |
0.41 | 9 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ibrahim Badr | 1 | 93 | 5.70 |
Ian McGraw | 2 | 253 | 24.41 |
James Glass | 3 | 3123 | 413.63 |