Presentation | 2002/12/12 Large Vocabulary ASR System based on the Hybrid HMM/BN model Konstantin MARKOV, Satoshi NAKAMURA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In current HMM based speech recognition systems, it is difficult to supplement acoustic spectrum features with additional information such as pitch, gender, articulator positions, etc. On the other hand, Dynamic Bayesian Networks (DBN) allow for easy combination of different features and make use of conditional dependencies between them. However, lack of efficient algorithms has prevented their application in large vocabulary continuous speech recognition. The hybrid HMM/BN acoustic model, where HMM are used for modeling of temporal speech characteristics and state probability model is represented by BN, provides a trade off solution to the problem. In this paper we describe the HMM/BN acoustic model and LVCSR system built upon this model. In the HMM/BN model, in addition to speech observation variable, state BN has two more discrete variables representing speaker gender and pitch frequency. Evaluation results on WSJ database showed lower word error rate with respect to the same complexity conventional HMM acoustic model when there is enough training data to estimate reliable HMM/BN parameters. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Hybrid HMM/BN / BN / DBN / LVCSR |
Paper # | NLC2002-51 |
Date of Issue |
Conference Information | |
Committee | NLC |
---|---|
Conference Date | 2002/12/12(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Natural Language Understanding and Models of Communication (NLC) |
---|---|
Language | ENG |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Large Vocabulary ASR System based on the Hybrid HMM/BN model |
Sub Title (in English) | |
Keyword(1) | Hybrid HMM/BN |
Keyword(2) | BN |
Keyword(3) | DBN |
Keyword(4) | LVCSR |
1st Author's Name | Konstantin MARKOV |
1st Author's Affiliation | ATR Spoken Language Translation Research Labs() |
2nd Author's Name | Satoshi NAKAMURA |
2nd Author's Affiliation | ATR Spoken Language Translation Research Labs |
Date | 2002/12/12 |
Paper # | NLC2002-51 |
Volume (vol) | vol.102 |
Number (no) | 527 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |