Dialect adaptation for Mandarin Chinese speech recognition
نویسندگان
چکیده
Many local or regional dialects exist in China. In case of mismatch between the dialect used to train the system and the dialect of the user, poor recognition accuracy is obtained. In this paper, we therefore investigate the development of a dialectspecific recognition system in Mandarin Chinese using standard adaptation techniques: a speaker-independent (SI) model trained on a source dialect (Beijing dialect) is adapted using a limited set of speech data of a target dialect (Taiwanese dialect).
منابع مشابه
Adapt Mandarin TTS system to Chinese dialect TTS systems
This paper deals with how to construct Text To Speech (TTS) systems for Chinese dialects. The proposed method adapts Chinese Mandarin TTS system to dialects TTS systems through representing dialect phonology by Mandarin phonology using phonology mappings, and adding dialect vocabulary in the front end to handle lexical difference. But not all Chinese dialects are suitable for applying this adap...
متن کاملOn Cross-Dialect and -Speaker Adaptation of Speaking Rate-Dependent Hierarchical Prosodic Model for a Hakka Text-to-Speech System
This paper presents an effective adaptation of an existing speaking rate-dependent hierarchical prosodic model (SRHPM) for Mandarin to construct the SR-HPM for Hakka, another Chinese dialect. Based on the cross-dialectal linguistic similarities in terms of syntactic and prosodic structures, the adaptation is formulated as a maximum a posteriori estimation (MAP) problem with the existing Mandari...
متن کاملHakka Pitch-contour Parameter Generation Using a Mandarin-trained Pitch-contour Model
In this paper, using an existing pitch-contour model of a Chinese dialect (Mandarin here) to generate pitch-contour parameters for another dialect’s sentences (Hakka here) is studied. This can be generally viewed as a pitch-contour model adaptation problem. We study this problem in hope to save tedious labors and research time needed to build a pitchcontour model for a specific Chinese dialect....
متن کاملAutomatic initial/final generation for dialectal Chinese speech recognition
Phonetic differences always exist between any Chinese dialect and standard Chinese (Putonghua). In this paper, a method, named automatic dialect-specific Initial/Final (IF) generation, is proposed to deal with the issue of phonemic difference which can automatically produce the dialect-specific units based on model distance measure. A dialect-specific decision tree regrowing method is also prop...
متن کاملA Super Phonetic System and Multi-dialect Chinese Speech Corpus for Speech Recognition
In this paper, we describe the work on Chinese multi-dialect speech processing. Based on the phonetic analysis of ten Chinese dialects, we have created a Chinese super phonetic system for the Chinese speech recognition. To exam this phonetic system and develop Chinese dialect speech technology, we are building a multi-dialect speech corpus, which includes 10 dialect areas and 2000 speakers.
متن کامل