Presentation 2000/12/14
State Selection using Context-Independent HMM for Fast Likelihood Calculation
Akinobu Lee, Tatsuya Kawahara, Kiyohiro Shikano,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We address a method to efficiently select Gaussian mixtures for fast acoustic likelihood computation. It makes use of context-independent models for selection and back-off of corresponding triphone models. Specifically, for the k-best phone models by the preliminary evaluation, triphone models of higher resolution are applied, and others are assigned likelihoods with the monophone models. This selection scheme assigns more reliable back-off likelihoods to the un-selected states than the conventional Gaussian selection based on a VQ codebook, Experimental results show that this method can achieves a comparable performance, and works much better under the aggressive pruning condition. Together with the phonetic tied-mixture (PTM) modeling, acoustic matching cost is reduced to almost 14% with little loss of accuracy.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) LVCSR / Gaussian selection / state selection / PTM
Paper # NLC2000-43,SP2000-91
Date of Issue

Conference Information
Committee NLC
Conference Date 2000/12/14(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) State Selection using Context-Independent HMM for Fast Likelihood Calculation
Sub Title (in English)
Keyword(1) LVCSR
Keyword(2) Gaussian selection
Keyword(3) state selection
Keyword(4) PTM
1st Author's Name Akinobu Lee
1st Author's Affiliation Nara Institute of Science and Technology()
2nd Author's Name Tatsuya Kawahara
2nd Author's Affiliation Kyoto University
3rd Author's Name Kiyohiro Shikano
3rd Author's Affiliation Nara Institute of Science and Technology
Date 2000/12/14
Paper # NLC2000-43,SP2000-91
Volume (vol) vol.100
Number (no) 520
Page pp.pp.-
#Pages 6
Date of Issue