| Paper: | SP-P11.11 | ||
| Session: | Topics in Large Vocabulary Continuous Speech Recognition | ||
| Time: | Thursday, May 20, 09:30 - 11:30 | ||
| Presentation: | Poster | ||
| Topic: | Speech Processing: Large Vocabulary Recognition/Search | ||
| Title: | LIGHTLY SUPERVISED AND DATA-DRIVEN APPROACHES TO MANDARIN BROADCAST NEWS TRANSCRIPTION | ||
| Authors: | Berlin Chen; National Taiwan Normal University | ||
| Jen-Wei Kuo; National Taiwan Normal University | |||
| Wen-Hung Tsai; National Taiwan Normal University | |||
| 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 is 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 is 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 11.99% character error rate on the Mandarin broadcast news collected in Taiwan. | ||
| Back | |||
Home -||-
Organizing Committee -||-
Technical Committee -||-
Technical Program -||-
Plenaries
Paper Submission -||-
Special Sessions -||-
ITT -||-
Paper Review -||-
Exhibits -||-
Tutorials
Information -||-
Registration -||-
Travel Insurance -||-
Housing -||-
Workshops