Investigation on Mandarin Broadcast News Speech Recognition
Abstract
This paper describes the authors' efforts in developing a competitive Mandarin broadcast news speech recognizer. They have successfully incorporated the most popular speech technologies into their system. More importantly, they present two novel algorithms for smoothing pitch features and segmenting Chinese characters into word units. In addition, they propose to borrow the principle of point-wise mutual information for creating a Chinese word lexicon automatically. Their final system achieved a 6.0% character error rate (CER) on dev04 and a 16.0% CER on eval04 with simpler acoustic models, less training data, and simpler decoding architecture compared with other state-of-the-art systems. This system is equally competitive.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 01, 2006
- Accession Number
- ADA450339
Entities
People
- Mei-yuh Hwang
- Takahiro Shinozaki
- Wen Wang
- Xin Lei
Organizations
- University of Washington