Presentation | 1999/12/20 AStudyonTree-BasedClusteringforSpeaker-IndependentGaussianMixtureHMMs Tsuneo Kato, Shingo Kuroiwa, Tohru Shimizu, Norio Higuchi, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Tree-based clustering is an effective method to share HMM states by clustering triphones based on phonetic questions. Previous researches on this method have been made on HMMs of single Gaussian output distributions due to computational restrictions. However, single Gaussian HMMs may not be sufficient to create appropriate topology (i.e. HMM state sharing). Furthermore, a significant amount of time is required to obtain Gaussian mixture HMMs for repetitive distribution splitting and embedded training. In this paper, we propose a tree-based clustering for Gaussian mixture HMMs based on distribution clustering. This method achieved 67% reduction on training time and 1-2% improvement in phoneme accuracy |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | |
Paper # | NLC99-99 |
Date of Issue |
Conference Information | |
Committee | NLC |
---|---|
Conference Date | 1999/12/20(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 | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | AStudyonTree-BasedClusteringforSpeaker-IndependentGaussianMixtureHMMs |
Sub Title (in English) | |
Keyword(1) | |
1st Author's Name | Tsuneo Kato |
1st Author's Affiliation | () |
2nd Author's Name | Shingo Kuroiwa |
2nd Author's Affiliation | |
3rd Author's Name | Tohru Shimizu |
3rd Author's Affiliation | |
4th Author's Name | Norio Higuchi |
4th Author's Affiliation | |
Date | 1999/12/20 |
Paper # | NLC99-99 |
Volume (vol) | vol.99 |
Number (no) | 523 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |