AI summary

This paper introduces a new voice search system for Japanese and Korean, addressing challenges like infinite vocabulary and multiple script languages by modeling completely in the written domain for language model and dictionary, achieving simplification and speed-up of the process to deal with new languages in general.

Abstract

This paper describes challenges and solutions for building a successful voice search system as applied to Japanese and Korean at Google. We describe the techniques used to deal with an infinite vocabulary, how modeling completely in the written domain for language model and dictionary can avoid some system complexity, and how we built dictionaries, language and acoustic models in this framework. We show how to deal with the difficulty of scoring results for multiple script languages because of ambiguities. The development of voice search for these languages led to a significant simplification of the original process to build a system for any new language which in in parts became our default process for internationalization of voice search.