Speaker-Independent Digit Recognition Using a Neural Network with Time-Delayed Connections

K. P. Unnikrishnan, J. J. Hopfield, D. W. Tank

Research output: Contribution to journalArticlepeer-review


Discussed is the capability of a small neural network to perform speaker-independent recognition of spoken digits in connected speech. The network uses time delays to organize rapidly changing outputs of symbol detectors over the time scale of a word, & is data driven & unclocked. New ideas & procedures developed to achieve useful accuracy in a speaker-independent setting are outlined, including improvement of feature detectors, self-recognition of word ends, reduction in network size, & division of speakers into natural classes. Quantitative experiments based on Texas Instruments (TI) digit databases are described.

Original languageEnglish (US)
Pages (from-to)108-119
Number of pages12
JournalNeural Computation
Issue number1
StatePublished - Dec 1 1992

All Science Journal Classification (ASJC) codes

  • General Psychology
  • General Arts and Humanities


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

Cite this