Search

3 Dec 2008: 1. IntroductionSpeech recognition systems are increasingly being built withfound data such as broadcast news and conversational tele-phone speech recordings. ... Therefore, the use ofMLLRDMT as a testing transform with other DSAT modelswas investigated.

19 May 2005: How-ever such a simple linear normalization scheme may not be pow-erful enough to normalize highly non-homogeneous speech data,such as broadcast news. ... Development ofthe CU-HTK 2004 Broadcast News Transcription System,Summited to ICASSP’05. [10] K.

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 ... This corpus will be referred to as BN-train96. A further tranche

9 Dec 2006: WHO REALLY SPOKE WHEN?FINDING SPEAKER TURNS AND IDENTITIES IN BROADCAST NEWS AUDIO. ... For exam-ple, speaker models can be built for people who are likely to be inthe broadcast (such as prominent politicians or main news anchorsand reporters).

16 Jun 2000: A more complex example is to automatically detect repeated events in a database of broadcasts which usually correspond to non-news items such as commercials or jingles. ... Since pre-recorded commercials and jingles are often re-broadcast several times,

8 Mar 2000: For speech transcription problems with widely varying speaker, channel and background conditions, such as broadcast news transcription, it is beneficial to include unsupervised test-data adaptation to individual speakers and data ... M A Siegler,

8 Mar 2000: The 1997 HTK Broadcast News Transcription SystemP.C. Woodland, T. Hain, S.E. ... 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

2 Mar 2009: 1. IntroductionSpeech recognition systems are increasingly being built withfound data such as broadcast news and conversational tele-phone speech recordings. ... Therefore, the use ofMLLRDMT as a testing transform with other DSAT modelswas investigated.

22 Jun 2007: UNSUPERVISED TRAINING FOR MANDARIN BROADCAST NEWS AND CONVERSATIONTRANSCRIPTION. L. Wang, M.J.F. ... Index Terms— Speech Recognition, unsupervised learning. 1. INTRODUCTION. For some tasks, such as Broadcast News (BN) transcription, audiodata can be

22 Jun 2007: 3. STT POST PROCESSING. In processing data such as Broadcast News (BN) or Broadcast Con-versations (BCs) for an STT system, the first stage is to segment thedata into homogeneous blocks, ... 12] B. Xiang, L. Nguyen, X. Guo, and D. Xu, “The BBN

22 Feb 2007: Thishas allowed large vocabulary continuous speech recognition(LVCSR) tasks, such as Broadcast News transcription [1],to be addressed. ... Howeverfor tasks such as speech recognition often T > L since thesample rate of the observations is fixed.

10 Oct 2007: F. Gales. Abstract— Large vocabulary speech recognition systems areoften built using found data, such as broadcast news. ... I. INTRODUCTION. A DAPTIVE training [1], [2] has become increasinglypopular as greater use has been made of found data, suchas

11 Jan 2008: 1. INTRODUCTION. Adaptive training [1, 2] has become popular as the use of founddata, such as Broadcast News, has increased. ... It is interesting to compare this lower bound approximationfor recognition to standard iterative approaches such as

2 Mar 2000: The 1996 Hub-4 Broadcast News Transcription development data was used for all the experiments reported in this paper. ... In tasks such as following (potentially unknown) speakers through broadcast news shows, where frame error is more important, the

13 May 2004: Knowing the location of other events such as station jingles,commercials or music can help reveal the broadcast structure and allow information-less portions tobe discarded, hence saving processing time, storage ... as convincing on the Broadcast News

2 Mar 2009: However, inmany applications, such as broadcast news transcription orconversational telephone speech, there is no transcriptionavailable for the test data. ... However, in theory this approach can beapplied to any form of linear transforms, such as

30 May 2007: Thishas allowed large vocabulary continuous speech recognition(LVCSR) tasks, such as Broadcast News transcription [1],to be addressed. ... Sinha,. and S.E. Tranter, “Progress in the CU-HTK Broadcast News tran-scription system,” IEEE Transactions Audio

8 Mar 2000: Thus ‘words’ occurring in broadcast news whichrepresent hesitations in speech, such as uh-huh or hmmm were definedas stop words and finally some common function words which ap-peared to have ... to be made equivalent. A stemming excep-tions list was

23 Apr 2007: F. Gales. Abstract— Large vocabulary speech recognition systems areoften built using found data, such as broadcast news. ... I. INTRODUCTION. A DAPTIVE training [1], [2] has become increasinglypopular as greater use has been made of found data, suchas

23 Dec 2004: 6 Language Modelling and Word Lists. In most speech transcription tasks such as for example dictation or Broadcast News transcriptionlarge amounts of representative text data are available. ... 50000 most frequent words occurring in 204 million words