Lexical stress recognition using hidden Markov models

Abstract

A probabilistic algorithm is described for the estimation of the lexical stress pattern of English words from the acoustic signal using hidden Markov models (HMMs) with continuous asymmetric Gaussian probability density functions. Adopting a binary stressed-unstressed syllable classification strategy two five-state HMMs of the left-to-right type were generated, one for each stress value. Training observation vectors were extracted from a corpus of bisyllabic stress-minimal word pairs and consisted of nine acoustic measurements based on fundamental frequency, syllabic energy and coarse linear prediction spectra. Evaluation of both models using a set of recordings of the same word pairs yielded an average stress recognition rate of 94%.

Keywords

This publication has 11 references indexed in Scilit:

Lexical stress determination and its application to large vocabulary speech recognition
Published by Institute of Electrical and Electronics Engineers (IEEE) ,2005
Modelling of speech using primarily prosodic parameters
Computer Speech & Language, 1987
An information-theoretic analysis of phonetic dictionary access
Computer Speech & Language, 1987
Continuously variable duration hidden Markov models for automatic speech recognition
Computer Speech & Language, 1986
Pitch Period Detection and Chaining: Method and Evaluation
Phonetica, 1983
Maximum likelihood estimation for multivariate observations of Markov sources
IEEE Transactions on Information Theory, 1982
The DRAGON system--An overview
IEEE Transactions on Acoustics, Speech, and Signal Processing, 1975
A Maximization Technique Occurring in the Statistical Analysis of Probabilistic Functions of Markov Chains
The Annals of Mathematical Statistics, 1970
Some Acoustic Correlates of Word Stress in American English
The Journal of the Acoustical Society of America, 1960
Experiments in the Perception of Stress
Language and Speech, 1958