| Presentation | 2004/12/13 Design and Implementation of HMM/BN Acoustic Models Konstantin MARKOV, Satoshi NAKAMURA, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In recent years, the number of studies investigating new directions in speech modeling that goes beyond the conventional HMM has increased considerably. One promising approach is to use Bayesian Networks (BN) as speech model. Full recognition systems based on Dynamic BN as well as acoustic models using BN have been proposed lately. Our group at ATR has been developing the hybrid HMM/BN model which is a HMM where the state probability distribution is modeled by a BN, instead of commonly used mixture of Gaussian functions. In this paper, we describe the hybrid HMM/BN acoustic modeling framework especially emphasizing on some model design and implementation issues. The HMM/BN training is based on the Viterbi training paradigm and consists of two alternating steps - BN training and HMM transitions update. For recognition, in some cases, BN inference is computationally equivalent to mixture of Gaussians which allows HMM/BN model to be used in existing decoders without any modification. We present two examples of HMM/BN model application in speech recognition systems. Evaluations.under various conditions and for different tasks showed that the HMM/BN model gives consistently better performance than the standard mixture of Gaussians HMM. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | HMM/BN / acoustic model / Bayesian network |
| Paper # | NLC2004-43,SP2004-83 |
| Date of Issue |
| Conference Information | |
| Committee | NLC |
|---|---|
| Conference Date | 2004/12/13(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) | Design and Implementation of HMM/BN Acoustic Models |
| Sub Title (in English) | |
| Keyword(1) | HMM/BN |
| Keyword(2) | acoustic model |
| Keyword(3) | Bayesian network |
| 1st Author's Name | Konstantin MARKOV |
| 1st Author's Affiliation | Department of Acoustics and Speech Research, Spoken Language Translation Research Labs. ATR() |
| 2nd Author's Name | Satoshi NAKAMURA |
| 2nd Author's Affiliation | Department of Acoustics and Speech Research, Spoken Language Translation Research Labs. ATR |
| Date | 2004/12/13 |
| Paper # | NLC2004-43,SP2004-83 |
| Volume (vol) | vol.104 |
| Number (no) | 538 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |