Automatic classification of dialogue contexts for dialogue predictions

This paper exploits the broad concept of dialogue predictions by linking a point in a human-machine dialogue with a speci c language model which is used during the recognition of the next user utterance. The idea is to cluster several dialogue contexts into a class and to create a speci c language model for each class. We present an automatic algorithm based on the minimal decrease of mutual information which clusters the dialogue contexts. Moreover the algorithm is able to guess an appropriate number of classes, that gives a good trade o between the mutual information and the amount of training data. This automatic classi cation procedure allows the full automatic creation of context-dependent language models for a spoken dialogue system.

[1]  John J. Godfrey,et al.  SWITCHBOARD: telephone speech corpus for research and development , 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[2]  Bernhard Rüber,et al.  Context-dependent probability adaptation in speech understanding , 1997, Comput. Speech Lang..

[3]  Morena Danieli,et al.  A robust system for human-machine dialogue in telephony-based applications , 1997, Int. J. Speech Technol..

[4]  François Andry.  Static and dynamic predictions : a method to improve speech understanding in cooperative dialogues , 1992, ICSLP.

[5]  Pascale Fung,et al.  The estimation of powerful language models from small and large corpora , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[6]  Gerhard Th. Niedermair,et al.  Linguistic modelling in the context of oral dialogue , 1992, ICSLP.

[7]  Paolo Baggia,et al.  Specialized language models using dialogue predictions , 1996, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[8]  Roberto Gemello,et al.  Continuous speech recognition with neural networks and stationary-transitional acoustic units , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[9]  Heinrich Niemann,et al.  Combining stochastic and linguistic language models for recognition of spontaneous speech , 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

[10]  Paolo Baggia,et al.  Partial parsing as a robust parsing strategy , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[11]  Morena Danieli,et al.  Contextual Information and Specific Language Models for Spoken Language Understanding , 1997, ArXiv.