Abstract
The aim of the paper is to focus on a new approach to automatic speech recognition in noisy environments where the noise has either stationary or non-stationary statistical characteristics. The aim is to perform automatic recognition of speech in the presence of additive car noise. The technique applied is based on a combination of the hidden Markov model (HMM) decomposition method, for speech recognition in noise, developed by Varga and Moore (1990) from DRA and the hybrid (HMM/RBF) recognizer containing hidden Markov models and radial basis function (RBF) neural networks, developed by Singer and Lippmann (1992) from MIT Lincoln Lab. The present authors modified the hybrid recognizer to fit into the decomposition method to achieve high performance speech recognition in noisy environments. The approach has been denoted the hybrid model decomposition method and it provides an optimal method for decomposition of speech and noise by using a set of speech pattern models and a noise model(s), each realized as an HMM/RBF pattern model
Original language | English |
---|---|
Title of host publication | Proceedings og the IEEE International Conference on Acoustics, Speech, and Signal Processing |
Volume | Volume 2 |
Publisher | IEEE |
Publication date | 1994 |
Pages | 657-660 |
ISBN (Print) | 07-80-31775-0 |
DOIs | |
Publication status | Published - 1994 |
Event | 1994 IEEE International Conference on Acoustics, Speech, and Signal Processing - Adelaide, Australia Duration: 19 Apr 1994 → 22 Apr 1994 Conference number: 19 http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=3104 |
Conference
Conference | 1994 IEEE International Conference on Acoustics, Speech, and Signal Processing |
---|---|
Number | 19 |
Country/Territory | Australia |
City | Adelaide |
Period | 19/04/1994 → 22/04/1994 |
Internet address |