The 'neural' phonetic typewriter

The factors that make speech recognition difficult are examined, and the potential of neural computers for this purpose is discussed. A speaker-adaptive system that transcribes dictation using an unlimited vocabulary is presented that is based on a neural network processor for the recognition of pho...

Full description

Saved in:
Bibliographic Details
Published in:Computer (Long Beach, Calif.) Calif.), 1988-03, Vol.21 (3), p.11-22
Main Author: Kohonen, T.
Format: Article
Language:English
Subjects:
Automatic speech recognition
Natural languages
Neural networks
Optical films
Pattern recognition
Speech recognition
Speech synthesis
Telephony
Text recognition
Vocabulary
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The factors that make speech recognition difficult are examined, and the potential of neural computers for this purpose is discussed. A speaker-adaptive system that transcribes dictation using an unlimited vocabulary is presented that is based on a neural network processor for the recognition of phonetic units of speech. The acoustic preprocessing, vector quantization, neural network model, and shortcut learning algorithm used are described. The utilization of phonotopic maps and of postprocessing in symbolic forms are discussed. Hardware implementations and performance of the neural networks are considered.< >
ISSN:0018-9162
1558-0814
DOI:10.1109/2.28