![]() |
EUROSPEECH 2001 Scandinavia
|
![]() |
This paper describes a collaboration between Bell Labs and NHK (Japan Broadcasting Corp.) STRL to develop a real-time large vocabulary speech recognition system for live closed-captioning of NHK news programs. Bell Labs broadcast news recognition engine consists of a two-pass decoder using bigram language models (LM) and right biphone models during the first pass, and trigram LM with within-word triphone models in the second pass. Various pruning strategies are used to achieve real time decoding, together with a noise compensation procedure aimed at improving recognition on noisy segments of the program. The system operates in a real-time mode and delivers less than 2% of word error rate (WER) on studio news conditions and about 5% of WER on noisy news and reporter speech when evaluated on a real broadcast news program.
Bibliographic reference. Siohan, Olivier / Ando, Akio / Afify, Mohamed / Jiang, Hui / Lee, Chin-Hui / Li, Qi / Liu, Feng / Onoe, Kazuo / Soong, Frank K. / Zhou, Qiru (2001): "A real-time Japanese broadcast news closed-captioning system", In EUROSPEECH-2001, 495-498.