@inproceedings{32539faf21984283958fa2670b066b3d,
title = "Improved Mandarin speech recognition by lattice rescoring with enhanced tone models",
abstract = "Tone plays an important lexical role in spoken tonal languages like Mandarin Chinese. In this paper we propose a two-pass search strategy for improving tonal syllable recognition performance. In the first pass, instantaneous F0 information is employed along with corresponding cepstral information in a 2-stream HMM based decoding. The F0 stream, which incorporates both discrete voiced/unvoiced information and continuous F0 contour, is modeled with a multi-space distribution. With just the first-pass decoding, we recently reported a relative improvement of 24\% reduction of tonal syllable recognition errors on a Mandarin Chinese database [5]. In the second pass, F0 information over a horizontal, longer time span is used to build explicit tone models for rescoring the lattice generated in the first pass. Experimental results on the same Mandarin database show that an additional 8\% relative error reduction of tonal syllable recognition is obtained by the second-pass search, lattice rescoring with enhanced tone models.",
keywords = "Lattice rescoring, Supra-tone units, Tonal syllable recognition, Tone modeling",
author = "Huanliang Wang and Yao Qian and Frank Soong and Zhou, \{Jian Lai\} and Jiqing Han",
year = "2006",
doi = "10.1007/11939993\_47",
language = "英语",
isbn = "3540496653",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
pages = "445--453",
booktitle = "Chinese Spoken Language Processing - 5th International Symposium, ISCSLP 2006, Proceedings",
note = "5th International Symposium on Chinese Spoken Language Processing, ISCSLP 2006 ; Conference date: 13-12-2006 Through 16-12-2006",
}