4th International Conference on Spoken Language Processing

Philadelphia, PA, USA
October 3-6, 1996

Anchor Point Detection for Continuous Speech Recognition in Spanish: The Spotting of Phonetic Events

Manuel A. Leandro (2), José M. Pardo (1)

(1) E.T.S. Ingenieros de Telecomunicación, Universidad Polítécnica de Madrid, Spain
(2) Universidad Alfonso X el Sabio. Villanueva de la Cañada, Madrid, Spain

Several techniques have been used to constraint the search space in an HMM based continuous speech recognition system (grammar, beam search, etc.) in order to reduce computation without significant lose in performance [1]. The use of anchor points is a state-of-the-art technique that has already been used in some systems [2][3][4]. This approach has lead us to a bottom-up strategy in a continuous speech recognition system in which the first module performs the spotting of predefined phonetic events and the second module uses them as anchor points in order to guide the HMM-based recognition task. This paper describes the definition of phonetic events for Spanish (based on expert knowledge of language) and the algorithms used for their detection and classification. Figures of performance are presented.

Full Paper

Bibliographic reference.  Leandro, Manuel A. / Pardo, José M. (1996): "Anchor point detection for continuous speech recognition in Spanish: the spotting of phonetic events", In ICSLP-1996, 2336-2339.