logo
CanyamAI summaries for academic research
language
MobileMobile
  • Phone FeatureWeChat Mini Program
EnglishEnglish
noticeNotice
BlogBlog
delete
arrow
Return

Tree-structured vector quantization for speech recognition

delete2000-07-01
delete6
PRE
AI
M
M. Barszcz
W
Wanyi Chen
G
Gilles Boulianne
P
Patrick Kenny
DOI：10.1006/csla.2000.0143delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
We describe some new methods for constructing discrete acoustic phonetic hidden Markov models (HMMs) using tree quantizers having very large numbers (16-64 K) of leaf nodes and tree-structured smoothing techniques. We consider two criteria for constructing tree quantizers (minimum distortion and minimum entropy) and three types of smoothing (mixture smoothing, smoothing by adding 1 and Gaussian smoothing). We show that these methods are capable of achieving recognition accuracies which are generally comparable to those obtained with Gaussian mixture HMMs at a computational cost which is only marginally greater than that of conventional discrete HMMs. We present some evidence of superior performance in situations where the number of HMM distributions to be estimated is small compared with the amount of training data. We also show how our methods can accommodate feature vectors of much higher dimensionality than are traditionally used in speech recognition. (C) 2000 Academic Press.

Journal

C
Computer Speech and Language
IF:
3.4
Papers:
1.5K
Citations:
2.6K

Organization

No organization information available