Exploring the Back-Propagation Network for Speech Applications
Abstract
Neural networks have sophisticated abilities for processing and filtering signals. In particular, Elman and Zipser demonstrated that the back- propagation network develops significant feature representations which may be useful for both segmenting and recognizing speech. Such networks might find applications in speech compression and/or normalization. The network's apparent potential for speech applications justifies further exploration, and this paper describes our work in progress.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jun 01, 1988
- Accession Number
- ADA197385
Entities
People
- Doug Martin
- Jeff Waters
- Stephen Luse
- Stephen Nunn