Automatic generation of pronunciation lexicons for Mandarin spontaneous speech
Bill Byrne, Veera Venkataramani, Terri Kamm, Thomas Fang Zheng, Ziqi Song, Pascale Fung, Yui Man Lui, Umar Ruhi · 2002
Pronunciation modeling for large vocabulary speech recognition attempts to improve recognition accuracy by identifying and modeling pronunciations that are not in the ASR systems pronunciation lexicon. Pronunciation variability in spontaneous Mandarin is studied using the newly created CASS corpus of phonetically annotated spontaneous speech. Pronunciation modeling techniques developed for English,are applied to this corpus to train pronunciation models which are then used for Mandarin broadcast news transcription.