Information Services banner Edinburgh Research Archive The University of Edinburgh crest

Edinburgh Research Archive >
Centre for Speech Technology Research >
CSTR publications >

Please use this identifier to cite or link to this item: http://hdl.handle.net/1842/1141

This item has been viewed 91 times in the last year. View Statistics

Files in This Item:

File Description SizeFormat
Fujinaga2001ICASSP.pdf98.97 kBAdobe PDFView/Open
Title: Multiple-Regression Hidden Markov Model
Authors: Fujinaga, Katsuhisa
Nakai, Mitsuru
Shimodaira, Hiroshi
Sagayama, Shigeki
Issue Date: 2001
Citation: In Proc. ICASSP 2001, May 2001.
Abstract: This paper proposes a new class of hidden Markov model (HMM) called multiple-regression HMM (MRHMM) that utilizes auxiliary features such as fundamental frequency (F0) and speaking styles that affect spectral parameters to better model the acoustic features of phonemes. Though such auxiliary features are considered to be the factors that degrade the performance of speech recognizers, the proposed MR-HMM adapts its model parameters, i.e. mean vectors of output probability distributions, depending on these auxiliary information to improve the recognition accuracy. Formulation for parameter reestimation of MRHMM based on the EM algorithm is given in the paper. Experiments of speaker-dependent isolated word recognition demonstrated that MR-HMMs using F0 based auxiliary features reduced the error rates by more than 20% compared with the conventional HMMs.
Keywords: hidden Markov model
multiple-regression HMM
speech
URI: http://hdl.handle.net/1842/1141
Appears in Collections:CSTR publications

Items in ERA are protected by copyright, with all rights reserved, unless otherwise indicated.

 

Valid XHTML 1.0! Unless explicitly stated otherwise, all material is copyright © The University of Edinburgh 2013, and/or the original authors. Privacy and Cookies Policy