Search

1 Aug 2005: Experimental results are presented on both broadcast news (BN) and conversational telephone speech (CTS) transcription tasks. |

23 Jun 2005: Using VTLN for Broadcast News Transcription. Proc. ICSLP 2004, October 2004 (Jeju Island, Korea). ... Speaker Diarisation for Broadcast News. Proc. Odyssey 2004 Speaker and Language Recognition Workshop, pp.

5 Apr 2005: Experimental results are presented on both broadcast news (BN) and conversational telephone speech (CTS) transcription tasks. |

15 Feb 2005: Recent Developments at Cambridgein Broadcast News Transcription. D.Y. Kim, H.Y. Chan, G. ... Presentation Overview. • RT03 Broadcast News System Review• Training & Test Data• Improved Acoustic Model Building. –

9 Aug 2005: THE APPLICABILITY OF ADAPTIVE LANGUAGE MODELLING FORTHE BROADCAST NEWS TASK. Philip Clarkson Tony Robinson. ... on cache-based and mixture-based modelsand their use on the Broadcast News task.

31 Mar 2005: The ELISA Consortium Approaches in Broadcast News Evaluation,''. in Proc. ICASSP, Montreal, May 2004, vol. ... S. E. Tranter and D. A. Reynolds,. ''Speaker Diarisation for Broadcast News,'' [in Proc.

15 Feb 2005: Fall 2004 RT-04 Workshop. 2Kim et al., ‘Recent Developments at Cambridge in Broadcast News Transcription’, Proc.

1 Apr 2005: DEVELOPMENT OF THE CU-HTK 2004 BROADCAST NEWS TRANSCRIPTION SYSTEMS. D.Y. Kim, H.Y. ... This has led to an order of magnitude increase intraining data for the US English broadcast news (BN-E) task.

22 Sep 2005: The experiments reported in this paper use a development set of 24 US broadcast news shows, denoted. ... S. E. Tranter and D. A. Reynolds,. ''Speaker Diarisation for Broadcast News,'' [in Proc.

10 Jan 2005: Acknowledgements. The authors would like to thank Kit Thambiratnam for work in broadcast news segmentation whilst at Cambridge University. ... The ELISA Consortium Approaches in Broadcast News Speaker Segmentation during the NIST 2003 Rich Transcription

19 May 2005: Experimental results are pre-sented on both broadcast news (BN) and conversational telephonespeech (CTS) transcription tasks. ... Development ofthe CU-HTK 2004 Broadcast News Transcription System,Summited to ICASSP’05. [10] K.

12 Apr 2005: Experimentalresults are presented based on the MPE trained Subspace for Pre-cision and Mean models, evaluated on both broadcast news andconversational telephone speech English tasks. ... Experimental results are presented based on two LVCSR Englishtasks:

22 Sep 2005: 953–956. [5] J.-L. Gauvain, L. Lamel, and G. Adda, “Partitioning andTranscription of Broadcast News Data,” in Proc. ... A. Reynolds, “Speaker Diarisationfor Broadcast News,” in Proc. Odyssey Speaker and Lan-guage Recognition Workshop, June 2004,

12 Jan 2005: Sim, and P. C. Woodland, “Recent Devel-opments at Cambridge in Broadcast News Transcription,”in Proc. ... F. Gales,D. Mrva, K. C. Sim, and P. C. Woodland, “Development ofthe CU-HTK 2004 Broadcast News Transcription Systems,”in Proc.

25 Mar 2005: Transcription evaluations.[1] It consists of30 minute extracts from 6 different US news shows broadcast inFebruary 2001. ... A. Reynolds, “Speaker Diarisation forBroadcast News,” in Proc. Odyssey Speaker and LanguageRecognition Workshop, Toledo, Spain

9 Aug 2005: Such techniques are currently used in many state-of-the-art systems for the transcription for broadcast news. ... Jardino. The LIMSI1998 Hub-4E Transcription System. In Proceedings ofDARPA Broadcast News Workshop, Herndon, Virginia,USA, 1999.

19 May 2005: Exper-imental results are presented on both broadcast news (BN) andconversational telephone speech (CTS) transcription tasks. ... The number of components per state is 16 on averagelevel. Three BN test sets were used, each of them contains six 30minutes

9 Aug 2005: broadcast news and conversational speech over thetelephone, explicit indications of capitalised words are not given. ... from the NIST 1998 Hub-4 broadcast news benchmark testswere used as test data for the evaluation of the proposed system.

10 Jan 2005: The Rich Transcription diarisation evaluations[1, 2, 3] providea framework to analyse the performance of such speaker diarisa-tion systems on Broadcast News (BN) data. ... 5] J.-L. Gauvain, L. Lamel, and G. Adda, “Partitioning andTranscription of

10 Jan 2005: This baseline was trained onCTS and broadcast news transcripts (500M words al-together). ... The class-based model had 350 classes trained on CTS transcripts.The broadcast news data included transcripts made bya company called PSM, transcripts released

10 Jan 2005: The Rich Transcription diarisation evaluations[1, 2, 3] providea framework to analyse the performance of such speaker diarisa-tion systems on Broadcast News (BN) data. ... 5] J.-L. Gauvain, L. Lamel, and G. Adda, “Partitioning andTranscription of

9 Aug 2005: The correlation between pause lengthsand sentence boundary marks was studied for broadcast news datain [8]. ... 3.1. Results: S SR. The first automatic capitalisation system was implemented by smallmodifications to the HTK Broadcast News (BN)

9 Aug 2005: for the 1998 NIST Hub-4 Information Extraction (Named Entity) Broadcast News Benchmark. ... broadcast news and to cope with input which does not have capitalisation information.

23 Jun 2005: 953–956. [5] J.-L. Gauvain, L. Lamel, and G. Adda, “Partitioning andTranscription of Broadcast News Data,” in Proc. ... A. Reynolds, “Speaker Diarisationfor Broadcast News,” in Proc. Odyssey Speaker and Lan-guage Recognition Workshop, June 2004,

12 May 2005: The performance of these methods is evaluated by task, bydata source (broadcast news versus spontaneous telephone conver-sations) and by whether transcriptions come from humans or froman (errorful) automatic speech recognizer. ... 2.3. MDE Corpora.

26 Sep 2005: phone conversation and broadcast news transcriptions. The standard HTK release [60] without.

10 Jan 2005: Using VTLN for Broadcast News Transcription. D.Y. Kim, S. Umesh, M.J.F. ... Mrva, S. Tranter,L. Wang and P.C. Woodland, “Recent Advances in Broad-cast News Transcription,” Proc.

9 Aug 2005: N-gram word-level language modelswere constructed by training separate models on transcriptions ofthe Hub5 acoustic training data and on Broadcast News data andthen merging the resultant language models to effectively ... In order to accommodate both