Title :
Parallel distributed binary mapping models for speech recognition
Author :
Li, Jianmin ; Fang, Ditang
Author_Institution :
Dept. of Comput. Sci., Tsinghua Univ., Beijing, China
Abstract :
In this paper, we present a parallel distributed binary mapping models (PDBMM) approach to speech recognition, which is characterized by the following important properties. (1) Based on parallel processing, a PDBMM is constructed for speaker-independent large-vocabulary speech recognition, which optimally combines the techniques of neural networks and HMM. (2) A PDBMM is made up of a certain number of time-sequence binary classifiers (TSBC) which are designed to extract or fire low level acoustic events for basic speech units of modeling. PDBMM deals with speech recognition parallelly and allows to form the arbitary nonlinear decision surfaces more efficiently and rapidly. (3) The Time-Sequence arrangement will enable the TSBC to extract low level acoustic events and the temporal relationships between them. The evaluation results is very inspiring and shows the great potentiality of PDBMM in speech recognition
Keywords :
feedforward neural nets; hidden Markov models; parallel processing; pattern classification; speech recognition; HMM; evaluation results; feed forward neural networks; large vocabulary; low level acoustic events; nonlinear decision surfaces; parallel distributed binary mapping models; parallel processing; speaker-independent speech recognition; speech recognition; speech units; temporal relationships; time-sequence binary classifiers; Automatic speech recognition; Computer networks; Computer science; Concurrent computing; Fires; Hidden Markov models; Neural networks; Parallel processing; Pattern recognition; Speech recognition;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1994. ICASSP-94., 1994 IEEE International Conference on
Conference_Location :
Adelaide, SA
Print_ISBN :
0-7803-1775-0
DOI :
10.1109/ICASSP.1994.389270