Search
Search Funnelback University
- Refined by:
- Date: 2005
1 -
10 of
97
search results for news |u:mi.eng.cam.ac.uk
Fully-matching results
-
Abstract for liu_icassp05
mi.eng.cam.ac.uk/reports/abstracts/speech/liu_icassp05.html1 Aug 2005: Experimental results are presented on both broadcast news (BN) and conversational telephone speech (CTS) transcription tasks. | -
HTK Rich Audio Transcription - References
mi.eng.cam.ac.uk/research/projects/EARS/references.html23 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. -
Speech-Driven Cartoon Animation with Emotions Yan Li, Feng Yu* ...
mi.eng.cam.ac.uk/~mjfg/local/4F10/emot.pdf11 Nov 2005: hn). Since these templatesrepresent the lip configuration well, any new configurationcan be approximated by a linear combination of the proto-lips. ... n,j = 1. 18). 5.3 Audio to Visual MappingGiven a new audio clip, we first segment the audio signalinto -
abstract for gales_rt04_modeling
mi.eng.cam.ac.uk/reports/abstracts/speech/gales_rt04_modeling.html5 Apr 2005: Experimental results are presented on both broadcast news (BN) and conversational telephone speech (CTS) transcription tasks. | -
Recent Developments at Cambridgein Broadcast News Transcription D.Y.…
mi.eng.cam.ac.uk/research/projects/EARS/pubs/kim_rt04.pdf15 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. – -
The Cambridge University March 2005 Speaker Diarisation System
mi.eng.cam.ac.uk/reports/full_html/sinha_eurospeech05.html/22 Sep 2005: These new models are then used to resegment the data using a Viterbi decode. ... S. E. Tranter and D. A. Reynolds,. ''Speaker Diarisation for Broadcast News,'' [in Proc. -
BN-E Experiments in Cambridge Do Yeong Kim, Mark Gales, ...
mi.eng.cam.ac.uk/research/projects/EARS/pubs/kim_sttmar05.pdf12 Apr 2005: BN-E Experiments in Cambridge. Conclusion. • New acoustic models were built with additional training data. ... The new models also showed 0.4% abs better performance on eval04 inP1P2 framework with adaptation. • -
Two-way Cluster Voting to Improve Speaker Diarisation Performance
mi.eng.cam.ac.uk/reports/full_html/tranter_icassp05.html/31 Mar 2005: 30 minute extracts from 6 different US news shows broadcast in February 2001. ... S. E. Tranter and D. A. Reynolds,. ''Speaker Diarisation for Broadcast News,'' [in Proc. -
The Development of the Cambridge UniversityRT-04 Diarisation System…
mi.eng.cam.ac.uk/research/projects/EARS/pubs/tranter_rt04.pdf15 Feb 2005: Viterbi decoding using new models then resegments the data. • First few iterations used diagonal covariance to model segments as there weremany short segments. • ... RT-04f RT-04f RT-04f 23.86 24.12† Official evaluation submission. • New -
THE APPLICABILITY OF ADAPTIVE LANGUAGE MODELLING FORTHE BROADCAST…
mi.eng.cam.ac.uk/reports/svr-ftp/auto-pdf/clarkson_icslp98.pdf9 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.
Search history
Recently clicked results
Recently clicked results
Your click history is empty.
Recent searches
- `download it here` |u:techpolicymphil.blog.jbs.cam.ac.uk (1) · moments ago
- TALK:Vb20 24 / |u:www.dpmms.cam.ac.uk (722) · moments ago
Recent searches
Your search history is empty.