Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

The ''neural'' phonetic typewriter

Journal Article · · Computer; (United States)
DOI:https://doi.org/10.1109/2.28· OSTI ID:5263327

Recently, researchers have placed great hopes on artificial neural networks to perform such ''natural'' tasks as speech recognition. This was indeed one motivation for us to start research in this area many years ago at Helsinki University of Technology. This article describes the result of that research - a complete ''neural'' speech recognition system, which recognizes phonetic units, called phonemes, from a continuous speech signal. Although motivated by neural network principles, the choices in design must be regarded as a compromise of many technical aspects of those principles. As our system is a genuine ''phonetic typewriter'' intended to transcribe orthographically edited text from an unlimited vocabulary, it cannot be directed compared with any more conventional, word-based system that applies classical concepts such as dynamic time warping and hidden Markov models.

Research Organization:
Helsinki Univ. of Technology (FI)
OSTI ID:
5263327
Journal Information:
Computer; (United States), Journal Name: Computer; (United States) Vol. 21:3; ISSN CPTRB
Country of Publication:
United States
Language:
English

Similar Records

Speech recognition and understanding
Journal Article · Sun May 01 00:00:00 EDT 1983 · Cybernetics (Engl. Transl.); (United States) · OSTI ID:6633905

Neural speech recognition: continuous phoneme decoding using spatiotemporal representations of human cortical activity
Journal Article · Wed Aug 03 00:00:00 EDT 2016 · Journal of Neural Engineering · OSTI ID:1523618

Application of backpropagation neural networks to phonetic element classification
Conference · Sun Dec 31 23:00:00 EST 1989 · OSTI ID:6321246