2005 · 41 citations · 7 references
ComputingComputer ScienceLinguisticsDialectologyNatural Language ProcessingPhoneticsLanguage ModelingLanguage ModelsMultilingual Natural Language ProcessingMultilingual ProcessingPhoneme SegmentationSpeech RecognitionChinese LinguisticsCode-switchingCode-switching ProcessingCode-switching Speech RecognitionData-driven Model ReductionLanguage Boundary DetectionLanguage SwitchingLanguage-dialect Boundary
In this paper, we present an effective method to detect the language boundary (LB) in code-switching utterances. The utterances are mainly produced in Cantonese, a commonly used Chinese dialect, whilst occasionally English words are inserted between Cantonese words. Bi-phone probabilities are calculated to measure the confidence that the recognized phones are in Cantonese. Two sets of context-independent mono-phone models are trained by monolingual Cantonese and monolingual English data separately. Both knowledge-based and data-driven model selection approaches are studied in order to retain the language-dependent characteristics and to merge duplicated phone sets between the two languages. The LB detection accuracy is 75.12% for utterances that contain one single code-switching word or phrase.
7
Spoken language resources for Cantonese speech processing
Tan Lee, W. K. Lo, P.C. Ching et al. · Speech Communication · 2002 · 136 citations
An acoustic-phonetic data base
William M. Fisher, Victor W. Zue, Jared Bernstein et al. · The Journal of the Acoustical Society of America · 1987 · 100 citations · Full text
Syllable classification using articulatory-acoustic features
Mirjam Wester · 2003 · 26 citations · Full text
Mixed language query disambiguation
Pascale Fung, CHEUNG Chi Shun · 1999 · 24 citations · Full text