Multilingual speech recognition: a unified approach
نویسندگان
چکیده
In this paper, we present a unified approach for hidden markov model based multilingual speech recognition. The proposed approach could be used across acoustically similar as well as diverse languages. We use an automatic phone mapping algorithm to map phones across languages and reduce the effective number of phones in the multililingual acoustic model. We experimentally verify the effectiveness of the approach using two acoustically similar languages, Tamil and Hindi and also American English which is very different from the other two languages acoustically. The experimental results are very encouraging and demonstrate the effectiveness of the approach in building a universal multilingual speech recognition system.
منابع مشابه
Comparing Three Methods to Create Multilingual Phone Models for Vocabulary Independent Speech Recognition Tasks
This paper presents three different methods to develop multilingual phone models for flexible speech recognition tasks. The main goal of our investigations is to find multilingual speech units which work equally well in many languages. With this universal set it is possible to build speech recognition systems for a variety of languages. One advantage of this approach is to share acoustic-phonet...
متن کاملRobust HMM training for unified dutch and German speech recognition
This paper describes our recent work in developing an unified Dutch and German speech recognition system in the SpeechDat domain. The acoustic component of the multiligual system is accomplished through sharing common phonemes without preserving any information about the languages. We propose a more robust MCE-based training algorithm, where only the language dependent phoneme models are allowe...
متن کاملSpotting Multilingual Consonant-Vowel Units of Speech Using Neural Network Models
Multilingual speech recognition system is required for tasks that use several languages in one speech recognition application. In this paper, we propose an approach for multilingual speech recognition by spotting consonant-vowel (CV) units. The important features of spotting approach are that there is no need for automatic segmentation of speech and it is not necessary to use models for higher ...
متن کاملMultilingual text-to-phoneme mapping
This paper introduces a novel approach for generating multilingual text-to-phoneme mappings for use in multilingual speech recognition systems. The multilingual mappings are based on the weighted outputs from a neural network text-to-phoneme model, trained on data mixed from several languages. The multilingual mappings used together with a branched grammar decoding scheme is able to capture bot...
متن کاملMultilingual Speech Recogn Identificat
This paper presents a new approach to multilingual speech recognition. The proposed algorithm combines both language identification (LID) and speech recognition into a single process. It is shown to be effective for multilingual grammarbased speech recognition where the language information is not available prior to recognition. The idea is to make use of acoustic-phonetic and lexical informati...
متن کامل