This paper describes the development of CU Corpora, a series of large-scale speech corpora for Cantonese. Cantonese is the most commonly spoken Chines...
There are many scenarios in both speech synthesis and coding in which adjacent time-frames of speech are spectrally discontinuous. This paper addresse...
The LDC began its first Broadcast News (BN) speech collection in the spring of 1996, facing a host of challenges including IPR negotiations with broad...
This paper describes connectionist techniques for recognition of Broadcast News. The fundamental difference between connectionist systems and more con...
This paper describes in detail the development of the HTK Broadcast News (BN) transcription system and presents full evaluation results from the 1996,...
