This paper describes an experimental approach to continuous speech recognition being carried out at IBM Research. It is based on statistical methods that allow automatic extraction of recognizer parameter values from speech data. Research results are presented for both artificial and natural recognition tasks.
Self-Organized Continuous Speech Recognition
Sae Technical Papers
1980 Automotive Engineering Congress and Exposition ; 1980
1980-02-01
Conference paper
English
Self-organized continuous speech recognition
Automotive engineering | 1980
|Continuous speech recognition without end-point detection
Online Contents | 2006
|Object Recognition from 2D Images using Kohonen Self-Organized Feature Maps
British Library Online Contents | 1997
|SPEECH RECOGNITION DEVICE, SPEECH RECOGNITION SYSTEM, AND SPEECH RECOGNITION METHOD
European Patent Office | 2019
|SPEECH RECOGNITION DEVICE, SPEECH RECOGNITION SYSTEM, AND SPEECH RECOGNITION METHOD
European Patent Office | 2020
|