Search

14 Aug 2000: This system gives a word error rate of 15.9% on the 1998 Hub4 broadcast news evaluation data. ... J. J. Odell, P. C. Woodland, and T. Hain. The CUHTK-Entropic 10xRT Broadcast News Transcription System.

14 Aug 2000: The system gives a word error rate of 15.9% on the 1998 Hub4 broadcast news evaluation data. ... Also a windowing system is being developed that allows automatic content dependent segmentation of news broadcasts.

8 Mar 2000: This paper presents the results from adding several forms of query expansion to our retrieval system running on several sets of transcriptions of broadcast news from the 1997 TREC-7 spoken ... A parallel corpus of 18628 documents from manually

1 Mar 2000: The CUHTK-Entropic 10xRT Broadcast News Transcription System. J.J. Odell , P.C. ... ABSTRACT. This paper describes the development of the CUHTK-Entropic 10xRT Broadcast News Transcription System.

1 Mar 2000: 133-137 (Lansdowne, VA, Feb. 1998). SEGMENT GENERATION AND CLUSTERING IN THE HTK BROADCAST NEWS TRANSCRIPTION SYSTEM. ... The distribution of broadcast news data suitable for GMM training can be seen in Table 1.

1 Mar 2000: Experiments in Broadcast News Transcription. P.C. Woodland, T. Hain, S.E. Johnson, T. ... FX. all other speech (e.g. spontaneous non-native). Table 1: Broadcast news focus conditions.

14 Aug 2000: The TREC-8 audio contains 500 hours of US broadcast news data that was recorded between February and June 1998. ... Transcription used a simplified version of the HTK broadcast news system which corresponds to the first-pass'' recognition system

8 Mar 2000: Use of these new clustering schemes has been shown to improve word error rates on the Hub4 1997 broadcast news evaluation data. ... M A Siegler, U Jain, B Raj & R M Stern. Automatic Segmentation, Classification and Clustering of Broadcast News [pp.

2 Mar 2000: FX. all other speech (e.g. spontaneous non-native). Table 1: Broadcast news focus conditions. ... Proc. 1998 DARPA Broadcast News Transcription and Understanding Workshop, pp. 41-48, Lansdowne.

8 Mar 2000: We show how the new algorithms can outperform extended Kalman filter (EKF) training. ... weights (eqn 1), evaluate the new importance ratios (eqns 3,4,5) and resample if necessary.