NAISTAR
Advanced Search
Japanese | English

naistar (NAIST Academic Repository) >
学術リポジトリ naistar / NAIST Academic Repository naistar >
国際会議発表論文 / Proceedings >
情報科学研究科 / Graduate School of Information Science >

Please use this identifier to cite or link to this item: http://hdl.handle.net/10061/7944

Title: Adaptation of Model Parameters by HMM Decomposition in Noisy Reverberant Environments
Authors: Tetsuya Takiguchi
Satoshi Nakamura
Qiang Huo
Kiyohiro Shikano
Issue Date: Apr-1997
Start page: 155
End page: 158
Abstract: This paper presents a new method to estimate HMM parameters of an acoustical transfer function based on HMM decomposition in model domain. The model parameters are estimated by maximizing a likelihood of adaptation data. The proposed method is obtained as the natural result of a reverse process of the HMM composition. In our previous paper, we proposed a method which can model an observed signal by the composition of HMMs of clean speech, noise and an acoustical transfer function. The previously proposed method needs measurement of impulse responses. It is inconvenient and unrealistic to me出ure impulse responses for a new environment. The new method is able to estimate HMM parameters of the acoustical transfer function from a small amount of adaptation data. Its effectiveness is confirmed by a series of speaker dependent and independent word recognition experiments on simulated distant-talking speech.
Description: ESCA-NATO Workshop on Robust Speech Recognition for Unknown Communication Channels, April 17-18, 1997, Pont-a-Mousson, France.
URI: http://hdl.handle.net/10061/7944
Text Version: Publisher
Appears in Collections:情報科学研究科 / Graduate School of Information Science

Files in This Item:

File SizeFormat
ESCA-NATO_1997_155.pdf638.03 kBAdobe PDFView/Open

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

 

Copyright (c) 2007-2012 Nara Institute of Science and Technology All Rights Reserved.
DSpace Software Copyright © 2002-2010  Duraspace - Feedback