Search

19 Apr 2000: 1163-1177 (Paris,France, April 2000). Audio Indexing and Retrieval of Complete Broadcast News Shows. ... This paper describes a system for retrieving relevant portions of complete broadcast news shows starting with only the audio data.

16 Jun 2000: measure. The technique has shown to be effective at finding small sections of cue audio and has been applied to automatically locating the end of broadcast news shows and finding ... In this case, some broadcast structure is revealed and the removal of

2 Mar 2000: For the task of identifying potentially unknown anchor speakers within broadcast news shows, the frame classification error rate is very important. ... In tasks such as following (potentially unknown) speakers through broadcast news shows, where frame

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: Experiments in Broadcast News Transcription. P.C. Woodland, T. Hain, S.E. Johnson, T. ... For acoustic training a number of US broadcast news shows (both television and radio) transmitted prior to June 30th 1996 were recorded and labelled by the LDC.

10 Apr 2000: Audio Indexing and Retrieval of Complete Broadcast News Shows. S.E. Johnson†, P. ... Abstract. This paper describes a system for retrieving relevant portions of complete broadcast news shows startingwith only the audio data.

1 Mar 2000: 41-48 (Lansdowne,VA, Feb. 1998). The 1997 HTK BROADCAST NEWS TRANSCRIPTION SYSTEM. ... For acoustic training a number of US broadcast news shows (both television and radio) transmitted prior to June 30th 1996 were recorded and labelled by the LDC.

8 Mar 2000: its performance using automatic transcriptions of about 50 hours of broadcast news data. ... The input data is presented to the HTK transcription system as complete episodes of broadcast news shows and these are first converted to a set of segments for

2 Mar 2000: The input data is presented to the system as complete episodes of broadcast news shows and these are first converted to a set of segments for further processing [9]. ... J. Young. Segment Generation and Clustering in the HTK Broadcast News Transcription

2 Mar 2000: The baseline acoustic corpus available in 1997 used recorded audio from various US broadcast news shows (television and radio). ... Proc. 1998 DARPA Broadcast News Transcription and Understanding Workshop, pp. 41-48, Lansdowne.

19 Apr 2000: The technique has shown to be effective at finding smallsections of cue audio and has been applied to automaticallylocating the end of broadcast news shows and finding non-news events such ... In this case, some broadcast structure is revealedand the

30 Mar 2000: Table 2: Description of query and relevance sets used. 2. The HTK Broadcast News Transcription System. ... 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

30 Mar 2000: The results show that automatic commercial elimination can be performed very successfully for ABC news shows. ... 1996 to Jan. 1998 (from the Primary Source Media Broadcast News collection) and Jan.

10 Apr 2000: For acoustic training a number of US broadcast news shows(both television and radio) transmitted prior to June 30th 1996were recorded and labelled by the LDC. ... spontaneous non-native). Table 1: Broadcast news focus conditions. For development test

8 Mar 2000: For acoustic training a number of US broadcast news shows(both television and radio) transmitted prior to June 30th 1996were recorded and labelled by the LDC. ... spontaneous non-native). Table 1: Broadcast news focus conditions. For development test

8 Mar 2000: 2. OVERVIEW OF THE HTK BROADCAST NEWSTRANSCRIPTION SYSTEM. The input data is presented to the HTK transcription system ascomplete episodes of broadcast news shows and these are first con-verted to ... of broadcast news texts, the LDC-distributed

10 Apr 2000: For the task of identifying potentially unknown anchorspeakers within broadcast news shows, the frame classi-fication error rate is very important. ... These methods were shown tobe an important part of our overall recognition systemfor broadcast news.

8 Mar 2000: The 1998 HTK Broadcast News Transcription System:Development and Results. P.C. Woodland, T. ... The baseline acoustic corpus available in 1997 used recordedaudio from various US broadcast news shows (television andradio).

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.

8 Mar 2000: spontaneous non-native). Table 3: 1996 H4 focus conditions. A number of broadcast news shows transmitted prior to June30th 1996 were recorded and labelled by the LDC for acous-tic training. ... 5. CONCLUSIONThis paper has described our initial efforts to