Title :
A comparison between HMM and hybrid ANN-HMM-based systems for continuous speech recognition
Author :
Ynoguti, Carlos Albeno ; Morais, Edmilson Da Silva ; Violaro, Fabio
Author_Institution :
Dept. de Comunicacoes, Univ. Estadual de Campinas, Sao Paulo, Brazil
Abstract :
The purpose of this paper is to compare the performance of two continuous speech recognition systems, one based on hidden Markov models (HMM) and the other based on hybrid artificial neural networks and hidden Markov models (ANN-HMM). The comparisons are in terms of recognition rate and in terms of computational complexity. Preliminary results points favorably to hybrid systems
Keywords :
computational complexity; hidden Markov models; neural nets; speech recognition; artificial neural networks; computational complexity; continuous speech recognition; hidden Markov models; hybrid ANN-HMM; performance; recognition rate; Artificial neural networks; Cepstral analysis; Computational complexity; Computer networks; Databases; Electronic mail; Hidden Markov models; Maximum likelihood estimation; Neural networks; Speech recognition;
Conference_Titel :
Telecommunications Symposium, 1998. ITS '98 Proceedings. SBT/IEEE International
Conference_Location :
Sao Paulo
Print_ISBN :
0-7803-5030-8
DOI :
10.1109/ITS.1998.713105
