Search

2 Mar 2000: Our retrieval system was run on 7 different sets of automatically transcribed broadcast news texts with a WER varying from 24.8% to 66.2%. ... The transcription of spoken documents was done using part of our HTK broadcast news transcription system [8].

1 Mar 2000: The rest of the paper is arranged as follows. We first give details of the broadcast news data used in the experiments, and briefly describe our work on segment processing which ... This was the scheme that we used in our 1996 broadcast news evaluation

14 Aug 2000: The audio, which comes in RealAudio format, is first converted into standard uncompressed format from which a transcription is produced using our large vocabulary broadcast news recognition engine. ... J. J. Odell, P. C. Woodland, and T. Hain. The

1 Mar 2000: Experiments in Broadcast News Transcription. P.C. Woodland, T. Hain, S.E. Johnson, T. ... The rest of the paper is arranged as follows. We first give details of the broadcast news data used, and then describe our work on segment processing (segmentation,

14 Aug 2000: The audio, which usually comes in RealAudio format, is first converted into standard uncompressed format from which a transcription is produced using our large vocabulary broadcast news recognition engine. ... Also a windowing system is being developed

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

10 Apr 2000: different sets ofautomatically transcribed broadcast news texts with aWER varying from24.8% to 66.2%. ... 4.2. Transcription System. The transcription of spoken documents was done usingpart of our HTK broadcast news transcription system[8].

10 Apr 2000: The rest of the paper is arranged as follows. We first give de-tails of the broadcast news data used, and then describe our workon segment processing (segmentation, classification and ... Young S.J. (1997) TheDevelopment of the 1996 Broadcast News

2 Mar 2000: For the task of identifying potentially unknown anchor speakers within broadcast news shows, the frame classification error rate is very important. ... The 1996 Hub-4 Broadcast News Transcription development data was used for all the experiments reported

2 Mar 2000: Our experiments with FD on broadcast news data show that overall we get very similar results to maximum likelihood training, although the training procedure gives a sizeable improvement in the FD ... Proc. 1998 DARPA Broadcast News Transcription and

8 Mar 2000: Cambridge, CB2 1PZ, UK. ABSTRACTThis paper describes our efforts in extending a large vocabularyspeech recognition system to handle broadcast news transcription.Results using the 1995 DARPA H4 evaluation data set are ... 5. CONCLUSIONThis paper has

12 Oct 2000: This gave a new word list with 54,537 words where most of the pronunciations were already available in our broadcast news (Hub4) dictionary. ... P.C. Woodland, M.J.F. Gales, D. Pye & S.J. Young (1997). Broadcast News Transcription Using HTK.

8 Mar 2000: The rest of the paper is arranged as follows. We first givedetails of the broadcast news data used in the experiments,and briefly describe our work on segment processing whichsplits the ... Thiswas the scheme that we used in our 1996 broadcast news

30 Mar 2000: The input data is presented to our HTK transcription system as complete episodes of broadcast news shows and these are first converted to a set of segments for further processing. ... It is not possible to draw any strong conclusions from our TREC-7

10 Apr 2000: These methods were shown tobe an important part of our overall recognition systemfor broadcast news. ... The speaker-adaptation scheme isthat used in our overall recognition system before speaker.

8 Mar 2000: The 1998 HTK Broadcast News Transcription System:Development and Results. P.C. Woodland, T. ... Our experiments with FD on broadcast news data show thatoverall we get very similar results to maximum likelihoodtraining, although the training procedure

5 Oct 2000: 50,000 words occurring in the 204 millionwords of broadcast news (BN) LM training data. ... This gave a newword list with 54,537 words where most of the pronunciations werealready available in our broadcast news (Hub4) dictionary.

8 Mar 2000: TREC-7 1. 2. THE HTK BROADCAST NEWS TRANSCRIPTIONSYSTEM. The input data is presented to our HTK transcription system as com-plete episodes of broadcast news shows and these are first ... Proc. DARPA Broadcast News Transcrip-tion and Understanding Workshop