Search

19 Apr 2000: This is particularly important for the case of broadcast news since the density of important up-to-date information is generally high, but topic changes occur frequently and information on a ... The experiments reported in this paper use the framework of

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. ... The HMMs for TREC-7 used HMMs trained on 70 hours of acoustic data and

10 Apr 2000: This corpus will be referred to as BN-train96. A further tranche of data of similar size was released in1997 to form in total 72 hours of broadcast news training ... 1997).Transcription of Broadcast News. Proc. Eurospeech’97, pp.907-910, Rhodes. [4]

8 Mar 2000: The1997 system used N-gram language models trained on 132million words of broadcast news texts, the LDC-distributed1995 newswire texts, and the transcriptions from BNtrain97(LMtrain97). ... Furthermore we pro-cessed additional transcriptions of broadcast

10 Apr 2000: The 500hours of broadcast news audio was filtered using an automaticscheme for detecting commercials, and then transcribed using a2-pass HTK speech recogniser which ran at 13 times real time.The ... The HMMs were trained using 146 hours of broadcast news

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 ... The HMMs for TREC-7 used HMMs trained on 70 hours of acous-tic data