Initial evaluation of hidden dynamic models on conversational speech
| Autor: | Joseph Picone, H. Richards, T. Kamm, R. Regan, Z. Ma, Mike Schuster, J. Bridle, Li Deng, S. Pike |
|---|---|
| Rok vydání: | 1999 |
| Předmět: |
Conversational speech
Computer science business.industry Speech recognition Feature vector computer.software_genre Task (project management) Variation (linguistics) Dynamic models Rule-based machine translation Artificial intelligence business Hidden Markov model computer Natural language processing |
| Zdroj: | ICASSP |
| DOI: | 10.1109/icassp.1999.758074 |
| Popis: | Conversational speech recognition is a challenging problem primarily because speakers rarely fully articulate sounds. A successful speech recognition approach must infer intended spectral targets from the speech data, or develop a method of dealing with large variances in the data. Hidden dynamic models (HDMs) attempt to automatically learn such targets in a hidden feature space using models that integrate linguistic information with constrained temporal trajectory models. HDMs are a radical departure from conventional hidden Markov models (HMMs), which simply account for variation in the observed data. We present an initial evaluation of such models on a conversational speech recognition task involving a subset of the SWITCHBOARD corpus. We show that in an N-best rescoring paradigm, HDMs are capable of delivering performance competitive with HMMs. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|