Search

8 Mar 2000: This paper deals with the segment processing strategies employed bythe 1997 HTK broadcast news transcription system. ... Johnson S.E., Tuerk A., Niesler T.R.& Young S.J. (1998) The 1997 HTK Broadcast News Transcrip-tion System.

16 Jun 2000: Of the 110 seconds worth of news'' rejected by the system with shorter windows, 24 seconds was due to an interview with Bill Clinton being re-broadcast, and the rest was ... P.C. Woodland, M.J.F. Gales, D. Pye & S.J. Young. The Development of the 1996

8 Mar 2000: The paper is organised as follows. Firstly an overview ofthe HTK broadcast news transcription system used to generatehigh quality automatic transcriptions is given. ... We have developed the IR system for the broadcast news taskand improved the stop list

2 Nov 2000: A mixture of broadcast news and newswire text was used as training data for the topic model, with 144 million words of Broadcast News text and 25 million words of Los ... Whittaker and S.J. Young, The 1997 HTK Broadcast News Transcription System''; DARPA

10 Apr 2000: Segment Generation and Clustering inthe HTK Broadcast News Transcription System Proc.1998 DARPA Broadcast News Transcription and Un-derstanding Workshop pp. ... The 1997HTK Broadcast News Transcription System Proc.1998 DARPA Broadcast News Transcription

8 Mar 2000: T Hain, S E Johnson, A Tuerk, P C Woodland & S J Young. Segment Generation and Clustering in the HTK Broadcast News Transcription System [pp. ... P C Woodland, M J F Gales, D Pye & S J Young. The Development of the 1996 HTK Broadcast News

8 Mar 2000: This system gave a word error rate of 16.2% in the1997 DARPA Hub4 broadcast news evaluation. ... The TREC-7 HTK SDR system uses the first two passes of the 1997HTK Broadcast News System [12] in a modified form for reducedcomputational requirement.

10 Apr 2000: Abstract. This paper describes a system for retrieving relevant portions of complete broadcast news shows startingwith only the audio data. ... 7 Conclusions. This paper has described a system for retrieving relevant portions of complete broadcast news

5 May 2000: 2. In contrast to the experiments described in [6] we foundthe explicit WER minimisation using word level posteriorsto be effective for the broadcast news system despite itsrelatively high overall accuracy. ... Johnson, T.R. Niesler,A. Tuerk, E.W.D.

10 Apr 2000: This system was shown to givegood performance in the 1996 DARPA/NIST broadcast news par-titioned evaluation (PE) [8]. ... that using the full system with adaptation resultsin a 20% decrease in word error rate on broadcast news.

3 May 2000: C. Woodland, and T. Hain. The CUHTK-Entropic 10xRT Broadcast News Transcription System. ... InProc. DARPA Broadcast News Workshop, pages 271–275,Herndon, VA, 1999. [3] A.

10 May 2000: We processed this data to automatically detect andremove commercials [2]. Transcription used a simplifiedversion of the HTK broadcast news system which corre-sponds to the “first-pass” recognition system describedin [2]. ... Thespeech recogniser uses

6 Nov 2000: The system uses word-based N-gramLMs estimated from an interpolation of Hub5 acoustic train-ing transcriptions and Broadcast News texts. ... The system operates in multiple passes. Triphone modelsare used in word lattice generation.

27 Sep 2000: in the rangeof 30 to 50 %, which are almost twice as high as for other difficulttasks like Broadcast News Transcription [7]. ... Young S.J. (1998) The 1997HTK Broadcast News Transcription System.Proc. DARPABroadcast News Transcription and Understanding

19 Apr 2000: 4. EXPT. 1 – END POINT DETECTION. The initial evaluation of the direct audio search procedurewas carried out in the context of trying to automaticallydetect the endpoint of a broadcast news episode. ... 10] P.C. Woodland, M.J.F. Gales, D. Pye & S.J.

10 Apr 2000: These methods were shown tobe an important part of our overall recognition systemfor broadcast news. ... Segment Generating and Clustering in theHTK Broadcast News Transcription System. Proc.1998 DARPA Broadcast News Transcription and Un-derstanding

10 Apr 2000: The HMMs were trained using 146 hours of broadcast news au-dio running up to 31st January 1998, supplied by the LDC andused for the 1998 Hub-4 task. ... The first model was built using 190 million wordsof broadcast news text, covering 1992-1996 (supplied

10 Apr 2000: A Focus Conditions for Broadcast News 21. B Files Required for Processing 21B.1 SPH Files. ... Broadcast News transcription is also complicated by the presence of different audio conditions.