Presentation 2008-12-09
Acoustic Model Training Technique for Speech Recognition Using Style Estimation with Multiple-Regression HMM
Yusuke IJIMA, Makoto TACHIBANA, Takashi NOSE, Takao KOBAYASHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We propose a technique for emotional speech recognition based on multiple-regression HMM (MRHMM). To achieve emotional speech recognition for an arbitrary speaker with a small amount of training data, we incorporate a speaker and style adaptation technique into speaker-dependent MRHMM-based emotional speech recognition. In the proposed technique, we first adapt the speaker-independent model to target speaker's respective styles with a small amount of speech data. Then, using obtained speaker- and style-adapted HMMs and low-dimensional style control vector for each training style, the regression matrices of MRHMM are estimated based on least square method and maximum likelihood estimation. We assess the performance of the proposed technique on the recognition of acted emotional speech uttered by both professional narrators and non-professional speakers and show the effectiveness of the technique.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) speech recognition / multiple-regression HMM (MRHMM) / speaker adaptation / style adaptation / style estimation
Paper # NLC2008-30,SP2008-85
Date of Issue

Conference Information
Committee NLC
Conference Date 2008/12/2(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) Acoustic Model Training Technique for Speech Recognition Using Style Estimation with Multiple-Regression HMM
Sub Title (in English)
Keyword(1) speech recognition
Keyword(2) multiple-regression HMM (MRHMM)
Keyword(3) speaker adaptation
Keyword(4) style adaptation
Keyword(5) style estimation
1st Author's Name Yusuke IJIMA
1st Author's Affiliation Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology()
2nd Author's Name Makoto TACHIBANA
2nd Author's Affiliation Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology
3rd Author's Name Takashi NOSE
3rd Author's Affiliation Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology
4th Author's Name Takao KOBAYASHI
4th Author's Affiliation Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology
Date 2008-12-09
Paper # NLC2008-30,SP2008-85
Volume (vol) vol.108
Number (no) 337
Page pp.pp.-
#Pages 6
Date of Issue