Search

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: different sets ofautomatically transcribed broadcast news texts with aWER varying from24.8% to 66.2%. ... The input data is presented to the system as com-plete episodes of broadcast news shows and these are.

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

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. ... of broadcast news texts, the LDC-distributed 1995newswire texts, and the

8 Mar 2000: This system gave a word error rate of 16.2% in the1997 DARPA Hub4 broadcast news evaluation. ... Proc. DARPA Broadcast News Transcrip-tion and Understanding Workshop, pp. 133-137, Feb. 1998.

8 Mar 2000: its performance using automatic transcriptions of about 50 hours of broadcast news data. ... This system gave a word error rate of 16.2% in the 1997 DARPA Hub4 broadcast news evaluation.

10 Apr 2000: These methods were shown tobe an important part of our overall recognition systemfor broadcast news. ... The 1996 Hub-4 Broadcast News Transcription develop-ment data was used for all the experiments reported inthis paper.

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.

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

5 Oct 2000: The system uses word-based N-gram LMs estimated from an interpolation of Hub5 acoustic training transcriptions and Broadcast News texts.

5 Oct 2000: A 4-gram language model was trained on the transcripts of the acoustic training data and additional broadcast news transcriptions.

5 Oct 2000: 50,000 words occurring in the 204 millionwords of broadcast news (BN) LM training data. ... 18. P.C. Woodland, M.J.F. Gales, D. Pye & S.J. Young (1997).Broadcast News Transcription Using HTK.Proc.

5 May 2000: It is also interesting tonote that the improvement is consistent over the varioustypes of data found in broadcast news. ... Johnson, T.R. Niesler,A. Tuerk, E.W.D. Whittaker, and S.J. Young. The1997 HTK Broadcast News Transcription System.

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.

8 Mar 2000: This paper presents two strategies for clustering broadcast news data segments (found by an automatic segmentation algorithm) for subsequent MLLR adaptation. ... M A Siegler, U Jain, B Raj & R M Stern. Automatic Segmentation, Classification and

2 Nov 2000: 2 Finding the TopicsA mixture of broadcast news and newswire text was usedas training data for the topic model, with 144 million wordsof Broadcast News text and 25 million words of ... 3 Building a Language ModelA word 4-gram language model was built

2 Mar 2000: The transcription of spoken documents was done using part of our HTK broadcast news transcription system [8]. ... J. Young. Segment Generation and Clustering in the HTK Broadcast News Transcription System [in Proc.

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

10 Apr 2000: A full-scale implementation is then de-scribed and tested on data from the 1996 Broadcast News database. ... 2. 1.2 DataThe data used throughout this project was from the 1996 Broadcast News database.

20 Apr 2000: Also a windowing systemis beingdevelopedthatallows automaticcontentdependentsegmentationof news broadcasts. Acknowledgements. This work is in partfundedby anEPSRCgrantreferenceGR/L49611. ... In Proc. DARPA Broadcast News Workshop,