EUROSPEECH 2001 Scandinavia
Within the framework of Natural Spoken Dialogue systems, this paper describes a method for dynamically adapting a Language Model (LM) to the dialogue states detected. This LM combines a standard n-gram model with Stochastic Finite State Automata (SFSAs). During the training process, the sentence corpus used to train the LM is split into several hierarchical clusters in a 2-step process which involves both explicit knowledge and statistical criteria. From the same sentence corpus, SFSAs are extracted in order to model longer contexts than the ones used in the standard n-gram model. A first decoding process calculates a word-graph as well as a first sentence hypothesis. This first hypothesis will be used to find the optimal sub-LM. Then, a rescoring process of the word graph using this LM is performed. By adapting the LM to the dialogue state detected, we show a statistically significant gain in WER on a dialogue corpus collected by France Telecom R&D.
Bibliographic reference. Esteve, Yannick / Bechet, Frederic / Nasr, Alexis / Mori, Renato De (2001): "Stochastic finite state automata language model triggered by dialogue states", In EUROSPEECH-2001, 725-728.