Automatic Speech Recognition Services in Common Telephone Network

A. Karpov and A. Ronzhin (Russia)


Information retrieval, speech recognition, morpheme representation, speech enhancement


The paper describes new automatic service intended for using telephone directory inquiries without human operator. The developed automatic speech recognition system for Russian language solves for processing the voice input and answering the queries of users. The electronic catalogue "Yellow Pages of Saint-Petersburg" containing information about firms and organizations is used for debugging. The development of such system for Russian language has some problems, connected with complex structure of word-formation of Russian language. The developed speech recognition system SIRIUS has one additional level of Russian language representation - morphemic level. As a result the size of vocabulary and time for speech processing are significantly decreased. The specifics of the automatic speech recognition through telephone line are discussed. The various filter techniques are applied for noise reduction and speech enhancement to improve the system performance. The dialogue model for voice control of electronic catalogue "Yellow Pages" and the experimental results are presented in the paper.

Important Links:

Go Back