Connected-Digit Speaker-Dependent Speech Recognition Using a Neural Network with Time-Delayed Connections

K. P. Unnikrishnan, John J. Hopfield, David W. Tank

Research output: Contribution to journalArticlepeer-review

43 Scopus citations

Abstract

An analog neural network that can be taught to recognize stimulus sequences has been used to recognize the digits in connected speech. The circuit computes in the analog domain, using linear circuits for signal filtering and nonlinear circuits for simple decisions, feature extraction, and noise suppression. An analog perceptron learning rule is used to organize the subset of connections used in the circuit that are specific to the chosen vocabulary. Computer simulations of the learning algorithm and circuit demonstrate recognition scores >99% for a single speaker connected-digit data base. There is no clock; the circuit is data driven, and there is no necessity for endpoint detection or segmentation of the speech signal during recognition. Training in the presence of noise provides noise immunity up to the trained level. For the speech problem studied here, the circuit connections need only be accurate to about 3-b digitization depth for optimum performance. The algorithm used maps efficiently onto analog neural network hard-ware: single chip microelectronic circuits based upon this algorithm can probably be built with current technology.

Original languageEnglish (US)
Pages (from-to)698-713
Number of pages16
JournalIEEE Transactions on Signal Processing
Volume39
Issue number3
DOIs
StatePublished - Mar 1991
Externally publishedYes

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Connected-Digit Speaker-Dependent Speech Recognition Using a Neural Network with Time-Delayed Connections'. Together they form a unique fingerprint.

Cite this