Title :
An HMM-based Text Segmentation Method Using Variational Bayes Approach and Its Application to LVCSR for Broadcast News
Author :
Koshinaka, Takafumi ; Iso, Ken-ichi ; Okumura, Akitoshi
Author_Institution :
Media & Inf. Res. Labs., NEC Corp., Kawasaki, Japan
fDate :
March 18-23, 2005
Keywords :
Bayes methods; hidden Markov models; information retrieval; parameter estimation; speech recognition; text analysis; vocabulary; HMM-based text segmentation; LVCSR; broadcast news; information retrieval techniques; large vocabulary continuous speech recognition; left-to-right hidden Markov model; model parameter estimation; model selection; news stories; sparse data; text stream; unsupervised text segmentation; variational Bayes framework; Broadcasting; Frequency; Hidden Markov models; Information retrieval; Laboratories; Large-scale systems; National electric code; Speech recognition; Streaming media; Vocabulary;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 2005. Proceedings. (ICASSP '05). IEEE International Conference on
Print_ISBN :
0-7803-8874-7
DOI :
10.1109/ICASSP.2005.1415156
