|
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/1842/989
|
| Title: | Asynchronous-Transition HMM |
| Authors: | Matsuda, Shigeki
Nakai, Mitsuru
Shimodaira, Hiroshi
Sagayama, Shigeki |
| Issue Date: | Jun-2000 |
| Citation: | Acoustics, Speech, and Signal Processing, 2000. ICASSP '00. Proceedings. 2000 IEEE International Conference on, Volume 2, 5-9 June 2000 Page(s):II1005 - II1008 |
| Publisher: | IEEE |
| Abstract: | We propose a new class of hidden Markov model (HMM) called asynchronous-transition HMM (AT-HMM). Opposed to conventional HMMs where hidden state transition occurs simultaneously to all features, the new class of HMM allows state transitions asynchronized between individual features to better model asynchronous timings of acoustic feature changes. In this paper, we focus on a particular class of AT-HMM with sequential constraints based on a novel concept of “state tying along time”. To maximize the advantage of the new model, we also introduce a feature-wise state tying technique. Speaker-dependent speech recognition experiments demonstrated error reduction rates more than 30% and 50% in phoneme and isolated word recognitions, respectively, compared with conventional HMMs |
| URI: | http://ieeexplore.ieee.org/
http://hdl.handle.net/1842/989 |
| Appears in Collections: | CSTR publications
|
Items in ERA are protected by copyright, with all rights reserved, unless otherwise indicated.
|
