Informatics Report Series



Related Pages

Report (by Number) Index
Report (by Date) Index
Author Index
Institute Index

Title:Speech Recognition Using Asynchronous Transition HMM
Authors: Shigeki Matsuda ; Mitsuru Nakai ; Hiroshi Shimodaira ; Shigeki Sagayama
Date:Jun 2003
Publication Title:IEICE Trans. (D-II)
Publication Type:Journal Article
Volume No:J86-D-II(6 Page Nos:741-754
We propose asynchronous-transition HMM (AT-HMM) that is based on asynchronous transition structures among individual features of acoustic feature vector sequences. Conventional HMM represents vector sequences by using a chain of states, each state has vector distributions of multi-dimensions. Therefore, the conventional HMM assumes that individual features change synchronously. However, this assumption seems over-simplified for modeling the temporal behavior of acoustic features, since cepstrum and its time-derivative can not synchronize with each other. In speaker-dependent continuous phoneme recognition task, the AT-HMMs reduced errors by 10% to 40%. In speaker-independent task, the performance of the AT-HMMs was comparable to conventional HMMs.
Links To Paper
this url is for the conference paper containing a subset of the full paper in Japanese
this url is for the conference paper containing a subset of the full paper in Japanese
Bibtex format
author = { Shigeki Matsuda and Mitsuru Nakai and Hiroshi Shimodaira and Shigeki Sagayama },
title = {Speech Recognition Using Asynchronous Transition HMM},
journal = {IEICE Trans. (D-II)},
year = 2003,
month = {Jun},
volume = {J86-D-II(6},
pages = {741-754},
url = {},

Home : Publications : Report 

Please mail <> with any changes or corrections.
Unless explicitly stated otherwise, all material is copyright The University of Edinburgh