Integrated Multilingual Speech Recognition Impact on Chinese Spoken Language Processing

The notion of integrated multilingualism is introduced as the basis for a novel approach to multilingual speech recog nition This approach enables training of the recognizer using the data from only source language s The trained recognizer is nevertheless deployable directly to new tar get languages The performance of the recognizer is incre mentally improved via a language adaptation strategy In this paper an overview is provided of a language universal feature based phonological model and of a dynamic pho netic model that in combination constitute the general framework of integrated multilingual speech recognition Some related speech recognition experiments in connec tion with this framework are described Finally impact of the new approach to Chinese spoken language processing is analyzed in terms of the need to develop a successful and uniform speech recognition strategy for a wide variety of Chinese dialects with little or no training data required for the dialects INTRODUCTION INTEGRATED