Presentation | 2004/12/13 Reformulating the HMM as a Trajectory Model Keiichi TOKUDA, Heiga ZEN, Tadashi KITAMURA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | We have shown that the HMM whose state output vector includes static and dynamic feature parameters can be reformulated as a trajectory model by imposing the explicit relationship between the static and dynamic features. The derived model, referred to as "trajectory HMM," can alleviate the limitations of HMMs: i) constant statistics within an HMM state and ii) independence assumption of state output probabilities. In this paper, we first summarize the definition and the training algorithm. Then, to show that the trajectory HMM is a proper generative model, we derive a new algorithm for sampling from the trajectory model, and show the result of an illustrative experiment. A speech recognition experiment demonstrates the consistency between training and decoding criteria is essential: the model should not only be traind as a trajectory model but also be used as a trajectory model in decoding, even though the trajectory model has the same parameterization as the standard HMM. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | HMM / speech recognition / speech synthesis / trajectory model / dynamic feature |
Paper # | NLC2004-48,SP2004-88 |
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) | Reformulating the HMM as a Trajectory Model |
Sub Title (in English) | |
Keyword(1) | HMM |
Keyword(2) | speech recognition |
Keyword(3) | speech synthesis |
Keyword(4) | trajectory model |
Keyword(5) | dynamic feature |
1st Author's Name | Keiichi TOKUDA |
1st Author's Affiliation | Graduate School of Engineering, Nagoya Institute of Technology() |
2nd Author's Name | Heiga ZEN |
2nd Author's Affiliation | Graduate School of Engineering, Nagoya Institute of Technology |
3rd Author's Name | Tadashi KITAMURA |
3rd Author's Affiliation | Graduate School of Engineering, Nagoya Institute of Technology |
Date | 2004/12/13 |
Paper # | NLC2004-48,SP2004-88 |
Volume (vol) | vol.104 |
Number (no) | 538 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |