Lightly supervised and data-driven approaches to Mandarin broadcast news transcription

Berlin Chen, Jen Wei Kuo, Wen Hung Tsai

Research output: Contribution to journalConference article

31 Citations (Scopus)

Abstract

This paper investigates the use of several lightly supervised and data-driven approaches to Mandarin broadcast news transcription. First, with a consideration of the special structural properties of the Chinese language, a fast acoustic look-ahead technique for estimating the unexplored part of speech utterance was integrated into the lexical tree search to improve the search efficiency, in conjunction with the conventional language model look-ahead technique. Then, a verification-based method for automatic acoustic training data acquisition was developed to make use of the large amount of untranscribed speech data. Finally, two alternative strategies for language model adaptation were further studied for accurate language model estimation. With the above approaches, the system yielded an 11.94% character error rate on the Mandarin broadcast news collected in Taiwan.

Original languageEnglish
Pages (from-to)I777-I780
JournalICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume1
Publication statusPublished - 2004 Sep 28
EventProceedings - IEEE International Conference on Acoustics, Speech, and Signal Processing - Montreal, Que, Canada
Duration: 2004 May 172004 May 21

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Lightly supervised and data-driven approaches to Mandarin broadcast news transcription'. Together they form a unique fingerprint.

  • Cite this