HMM/NN hybrids for continuous speech recognition

Author

Abdel Alim, Onsy A. ; Elboghdadly, Nemat ; El Shaar, Nazira M.

Author_Institution

Fac. of Eng., Alexandria Univ., Egypt

Volume

2

fYear

2001

fDate

2001

Firstpage

509

Abstract

The main goal of automatic speech recognition (ASR) is to produce a machine which will recognize accurately normal human speech from any speaker. The recognition system may be classified as speaker-dependent or speaker-independent and isolated-word or connected word. There are three approaches to research in automatic speech recognition (ASR); the acoustic-phonetic approach, the pattern recognition approach, and the database statistical approach. Two approaches of this kind: hidden Markov model (HMM) and artificial neural network (ANN) are presented in this paper

Keywords

hidden Markov models; neural nets; speech recognition; HMM/NN hybrids; acoustic-phonetic approach; artificial neural network; automatic speech recognition; connected word recognition; continuous speech recognition; database statistical approach; hidden Markov model; isolated-word recognition; pattern recognition approach; speaker-dependent recognition; speaker-independent recognition; Artificial neural networks; Automatic speech recognition; Hidden Markov models; Linear predictive coding; Loudspeakers; Neural networks; Pattern recognition; Spectral analysis; Speech analysis; Speech recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Radio Science Conference, 2001. NRSC 2001. Proceedings of the Eighteenth National

Conference_Location

Mansoura

Print_ISBN

977-5031-68-0

Type

conf

DOI

10.1109/NRSC.2001.929410

Filename

929410