European Conference on Speech Technology Edinburgh, Scotland, UK September 1987

Continuous Speech Understanding by Keyword Extraction in a Voice Mail System

Y. Ariki (1), H. Ohkawa (2), T. Sakai (1)

(1) Dept. of Information Science, Faculty of Engineering, Kyoto University, Kyoto, Japan
(2) Computer Works, Mitsubishi Electric Corp. Kamakura-city, Kanagawa, Japan

In this paper, a developing voice-mail system is described which extracts keywords from continuously spoken mail. In this keyword extraction, a bottom-up approach to hypothesize the keywords and a top-down approach to verify them are integrated. First, a phoneme sequence is recognized in bottom-up mode, then keywords are hypothesized on the phoneme sequence. Finally, keyword candidates are verified by recognizing the consonants in a top-down manner.

Full Paper

Bibliographic reference.  Ariki, Y. / Ohkawa, H. / Sakai, T. (1987): "Continuous speech understanding by keyword extraction in a voice mail system", In ECST-1987, 2256-2259.