4th International Conference on Spoken Language Processing
Philadelphia, PA, USA
A number of experiments have shown that it is possible to use production models for speech recognition tasks  and . We present here the first results of an adaptation of Maeda's statistic model. We have also demonstrated the importance of taking into account the static and dynamic characteristics of the speaker. Some preliminary results for the identification of V1-V2 sequences are also provided.
Bibliographic reference. Candille, Laurence / Méloni, Henri (1996): "Dynamic control of a production model", In ICSLP-1996, 2305-2308.