Lightly Supervised and Data-Driven Approaches to Mandarin Broadcast News Transcription

Berlin Chen ； Jen-Wei Kuo ； Wen-Hung Tsai

《中文計算語言學期刊》 10卷1期 (2005/03) Pp. 1-17

https://doi.org/10.30019/IJCLCLP.200503.0001

並列摘要

This article investigates the use of several lightly supervised and data-driven approaches to Mandarin broadcast news transcription. With the special structural properties of the Chinese language taken into consideration, a fast acoustic look-ahead technique for estimating the unexplored part of a speech utterance is integrated into lexical tree search to improve search efficiency. This technique is used in conjunction with the conventional language model look-ahead technique. Then, a verification-based method for automatic acoustic training data acquisition is proposed to make use of large amounts of untranscribed speech data. Finally, two alternative strategies for language model adaptation are studied with the goal of achieving accurate language model estimation. With the above approaches, the overall system was found in experiments to yield an 11.88% character error rate when applied to Mandarin broadcast news collected in Taiwan.

並列關鍵字

acoustic look-ahead ； lightly supervised acoustic model training ； language model adaptation ； Mandarin broadcast news

參考文獻

Chen, B.,J. W. Kuo,W. H. Tsai(2004).Lightly Supervised and Data-Driven Approaches to Mandarin Broadcast News Transcription.(Proc. IEEE International Conference on Acoustics, Speech, Signal processing).

Chen, B.,H. M. Wang,L. F. Chien,L.S. Lee(1998).A*-Admissible Key-Phrase Spotting with Sub-Syllable Level Utterance Verification.(Proc. International Conference on Spoken Language Processing).

Aubert, X. L.(2002).An Overview of Decoding Techniques for Large Vocabulary Continuous Speech Recognition.Computer Speech and Language.16,89-114.

Bacchiani, M.,B. Roark(2003).Unsupervised Language Model Adaptation.IEEE International Conference on Acoustics, Speech, Signal processing.1,224-227.

Bellegarda, J. R.(2004).Statistical Language Model Adaptation: Review and Perspectives.Speech Communication.42,93-108.