Dynamic language models for interactive speech applications

This work proposes the use of hierarchical LMs as an effective method both for e ciently dealing with contextdependent LMs in a dialogue system and for increasing the robustness of LM estimation and adaptation. Starting from basic LMs that express elementary semantic units, concepts, or data-types, sentence level LMs are recursively built. The resulting LMs may be a combination of grammars, word classes, and statistical LMs. Moreover, these LMs can be e ciently compiled into probabilistic recursive transition networks. A speech decoding algorithm directly exploits the recursive representation and produces the most probable parse tree matching the speech signal. The proposed approach has been implemented for a dataentry task which covers structured data, e.g. numbers, dates, and proper names, as well as free texts. In this task, the active LM must continuously change according to the current status, the active form, and the data entered so far. Finally, while the hierarchical approach results very convenient to cope with this task, it also looks very general and can give advantages in other applications, e.g. dictation.