@inproceedings{217c1149a2de4431babffa8b6ac980e1,
title = "Phonetic transcription using speech recognition technique considering variations in pronunciation",
abstract = "We propose a new approach for performing phonetic transcription of speech and text that combines automatic speech recognition (ASR) and grapheme -to- phoneme (G2P) techniques. By augmenting the text with speech and using automatic speech recognition with a sausage searching net constructed from multiple text pronunciations corresponding to human speech utterance, we are able to reduce the effort for phonetic transcription. By using a multiple pronunciation lexicon, a transcription error rate of 12.74% was achieved. Further improvement can be achieved by adapting the pronunciation lexicon with pronunciation variation (PV) rules and an error rate reduction of 17.11% could be achieved.",
keywords = "Automatic phonetic transcription, Chinese, Dialect, Pronunciation variation, Taiwanese",
author = "Liang, {Min Siong} and Lyu, {Ren Yuan} and Chiang, {Yuang Chin}",
year = "2007",
doi = "10.1109/ICASSP.2007.367175",
language = "英语",
isbn = "1424407281",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
pages = "IV109--IV112",
booktitle = "2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07",
note = "2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07 ; Conference date: 15-04-2007 Through 20-04-2007",
}