A speech recognition method based on the sequential multi-layer perceptrons

Wen Yuan Chen*, Sin-Horng Chen, Cheng Jung Lin

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

20 Scopus citations

Abstract

A novel multi-layer perceptrons (MLP)-based speech recognition method is proposed in this study. In this method, the dynamic time warping capability of hidden Markov models (HMM) is directly combined with the discriminant based learning of MLP for the sake of employing a sequence of MLPs (SMLP) as a word recognizer. Each MLP is regarded as a state recognizer to distinguish an acoustic event. Next, the word recognizer is formed by serially cascading all state recognizers. Advantages of both HMM and MLP methods are attained in this system through training the SMLP with an algorithm which combines a dynamic programming (DP) procedure with a generalized probabilistic descent (GPD) algorithm. Additionally, two sub-syllable SMLP-based schemes are studied through application of this method toward the recognition of isolated Mandarin digits. Simulation results confirm that the performance of the method is comparable to a well modeled continuous Gaussian mixture density HMM trained with the minimum error criterion. Not only does the SMLP require less trainable parameters than the HMM system, but the former is more convenient for analysing internal features. With the aid of internal feature selection, discarding the least useful parameters of SMLP without affecting its performance is relatively easy.

Original languageEnglish
Pages (from-to)655-669
Number of pages15
JournalNeural Networks
Volume9
Issue number4
DOIs
StatePublished - Jun 1996

Keywords

  • Dynamic programming
  • Generalized probabilistic descent
  • Hidden Markov methods
  • Multi-layer perceptrons
  • Neural network
  • Speech recognition

Fingerprint Dive into the research topics of 'A speech recognition method based on the sequential multi-layer perceptrons'. Together they form a unique fingerprint.

Cite this