ISCA Workshop on Multilingual Speech and Language Processing (MULTILING 2006) Center for Language and Speech Technology, Stellenbosch University, Stellenbosch, South Africa April 9-11, 2006

Non-native Pronunciation Modeling in a Command & Control Recognition Task: A Comparison between Acoustic and Lexical Modeling

Judith Kessens

TNO Human Factors, Soesterberg, The Netherlands

In order to improve automatic recognition of English commands spoken by non-native speakers, we have modeled non-native pronunciation variation of Dutch, French and Italian. The results of lexical and acoustical modeling appeared to be source language and speaker dependent. Lexical modeling only resulted in a substantial improvement (of 35%) for the French speakers. Acoustic model adaptation halved the word error rates for the Italian speakers, whereas no improvements were found by lexical modeling of frequently observed Italian-accented non-native pronunciation variants. The performance for the Dutch speakers only slightly improved by lexical and acoustic modeling.

Full Paper

Bibliographic reference.  Kessens, Judith (2006): "Non-native pronunciation modeling in a command & control recognition task: a comparison between acoustic and lexical modeling", In MULTILING-2006, paper 005.