Search

26 Jun 2024: ALTA Spoken Language Processing Technology (SLPT) Project. [Openings. We do not have any open positions currently. Dr Mengjie Qian gave an invited talk at the Second Language Acquisition with Speech and Language Technologies (SLASaLT) Workshop, in

Our goal is to develop new techniques for medical image acquisition and novel algorithms for visualisation and measurement that assist clinicians in diagnosis and treatment planning.

Current & New Research Projects..

14 May 2020: Babel intends to demonstrate the ability to generate a speech transcription system for any new language within one week to support keyword search performance for effective triage of massive amounts of

J. Lasenbly, A. Zisserman, R. Cipolla and H. C. Longuet-Higgins. New Geometric Techniques in Computer Vision.

27 Jul 2020: A range of new features were integrated and are described in detail. ... Major new features include the use of Minimum Phone Error training (MPE), third differential features in conjunction with an HLDA transform, speaker adaptive training (SAT), the use

27 Jul 2020: Abstract for woodland_darpa99. Proc DARPA Broadcast News Workshop, March 1999 (Herndon, VA). ... Whittaker. March 1999. This paper presents the development of the HTK broadcast news transcription system for the November 1998 Hub4 evaluation.

27 Jul 2020: Contact:Title A NEW METHOD FOR THE ACQUISITION OF ULTRASONIC STRAIN IMAGE VOLUMES.

27 Jul 2020: Broadcast News Slash Unit Boundary Detection task.

27 Jul 2020: Criminisi, J. Shotton, A. Blake, and P.H.S. Torr. 2003. A new algorithm is proposed for novel view generation in one-toone teleconferencing applications. ... Examples are given that demonstrate the robustness of the new algorithm to spatial and temporal

27 Jul 2020: The main drawbacks of using circular motion alone, namely the difficulty in adding new views and part of the object always being invisible, can be overcome by incorporating arbitrary general views ... of the object and registering its new profiles with

27 Jul 2020: WHO REALLY SPOKE WHEN? FINDING SPEAKER TURNS AND IDENTITIES IN BROADCAST NEWS AUDIO. ... S. E. Tranter. May 2006. Automatic speaker segmentation and clustering methods have improved considerably over the last few years in the Broadcast News domain.

27 Jul 2020: Several strategies for using the new system are investigated and the final system gives a diarisation error rate of 6.9% on the RT-04 Fall diarisation evaluation data when processing

27 Jul 2020: Evaluations are conducted in both broadcast news and spontaneous telephone conversations, using human transcriptions and speech recognition output. |

27 Jul 2020: Experimental results are presented based on the MPE trained Subspace for Precision and Mean models, evaluated on both broadcast news and conversational telephone speech English tasks. |

The Bitonic Filter: a new noise reduction filter based on a mixture of morphological and linear operations [2]. ... The locally adaptive Bitonic X Filter, which is a new, highly competitive, far better performing, filter [4].

R. Cipolla. Computer Vision in Human-Machine Interaction: False Starts and New Horizons. ... R. Cipolla. Visual motion of curves and surfaces. Royal Society Discussion Meeting on New Geometrical Techniques in Computer Vision, London, UK, (July) 1997.

27 Jul 2020: Using this approximation, a new acoustic model called the factor analysed HMM (FAHMM) is presented.

27 Jul 2020: The classifier is designed in a way that it supports online incremental learning and it can be thus re-trained to increase its adaptability to an input captured under a new

23 Feb 2006: Jin, M. Noamany, andT. Shultz, “The ISL RT-04 Mandarin Broadcast News evaluationsystem,” inProc. ... Xu, “The BBN MandarinBroadcast News transcription system,” inProc. Eurospeech,Lisbon, Portugal, September 2005.

Start drawing a new contour by clicking and releasing in one of the regions where a new section of contour is required. ... Then continue defining new contour points until you reach an existing (correct) section of contour.

This will create a new DICOM data set with MAR applied (using the current settings). ... New data is created in a sub-directory 'refined' and each file has the additional '_refined' tag added to the end of the existing file name.

23 Jun 2003: 2003 System structure 10xRT CTS. • Automatic segmentation. • Use new models from full system. •

10 Oct 2007: UNSUPERVISED TRAINING FOR MANDARIN BROADCAST NEWS AND CONVERSATIONTRANSCRIPTION. L. Wang, M.J.F. ... Woodland, and etc., “The cu-htk mandarin broadcast news transcription system,” inProc.ICASSP 2006, May, 2006, pp.

By default, the new file name will be of the form 'stradwin_data_1.sw', 'stradwin_data_2.sw' etc. ... When the exported voxel array is re-loaded into Stradwin, these will appear as new object contours.

19 Feb 2010: Our goal is to develop new techniques for medical image acquisition and novel algorithms for visualisation and measurement that assist clinicians in diagnosis and treatment planning.

Save sequence. This will save the whole sequence (if there is one) to a new set of images, applying the current processing to each as it does so. ... Check for updates. Checks whether there are any more recent versions of wxDicom and shows the new

8 Mar 2000: The 1998 HTK Broadcast News Transcription System:Development and Results. P.C. Woodland, T. ... Proc. 1998 DARPA Broad-cast News Transcription and Understanding Workshop, pp.133-137. 5.

If you then save this patch, you can in future import it as a new surface as described below. ... This smoothed measurement data is used to create the new surfaces as an adjustment to the original measurement surface.

19 Jun 2023: Language model:. • Trigram LM trained on ASR L2 manual transcriptions and Broadcast News English• su-RNNLM3 trained on semi-supervised ASR L2 transcriptions. • ... BEA Workshop 20193. H. Yannakoudakis et al, “A new dataset and method for

22 Jan 2018: yWh. ht2. t1t. xt1. New applications: voice as a user interface. • ... Speech-to-speech/text translation for any language • Support business in new areas e.g.

27 Jul 2020: Contact:Title IMPROVEMENTS IN ACCURACY AND SPEED IN THE HTK BROADCAST NEWS TRANSCRIPTION SYSTEM. ... Contact:Title SEGMENT GENERATION AND CLUSTERING IN THE HTK BROADCAST NEWS TRANSCRIPTION SYSTEM.

If you select more than three, the least recently selected landmark will be deselected to make way for the new one. ... This splitting can also be achieved by using the 'erase' tool in the 3D window, and the same tool can be used to create a new object

27 Jul 2020: Contact:Title THE 1998 HTK BROADCAST NEWS TRANSCRIPTION SYSTEM: DEVELOPMENT AND RESULTS. ... Contact:Title IMPROVEMENTS IN ACCURACY AND SPEED IN THE HTK BROADCAST NEWS TRANSCRIPTION SYSTEM.

27 Jul 2020: Contact:Title THE 1998 HTK BROADCAST NEWS TRANSCRIPTION SYSTEM: DEVELOPMENT AND RESULTS. ... Contact:Title IMPROVEMENTS IN ACCURACY AND SPEED IN THE HTK BROADCAST NEWS TRANSCRIPTION SYSTEM.

We are always looking for new students with knowledge and interest in one or more of the following areas:.

19 Apr 2016: Current & New Research Projects.

In Proc. IEEE Conf. on Computer Vision and Pattern Recognition, New York, USA (June) volume 1, pages 594-601, 2006.

27 Jul 2020: The new approach is instead, that space-time proximity and trajectory coherence through image space are used as the only probabilistic criteria for clustering.

Publications. Turmezei TD, Lomas DJ, Fotiadou A, Hopper MA, Poole KES. A new CT grading system for hip osteoarthritis. ... Severity mapping of the proximal femur: a new method for assessing hip osteoarthritis with computed tomography.

27 Jul 2020: Abstract for kim_icassp05. Proc. ICASSP 2005. DEVELOPMENT OF THE CU-HTK 2004 BROADCAST NEWS TRANSCRIPTION SYSTEMS. ... Sim, P.C. Woodland. March 2005. This paper describes our recent work on improving broadcast news transcription and presents details of

11 Mar 2011: recognition (Broadcast News Transcription).

Recently, we are developing high-resolution beamforming algorithms for coherent plane-wave compounding, a new ultrasound imaging modality. ... In our new approach, we analyze each beamformer as a spatial filter that decorrelates signals received at

to new slots and domains, and committees of experts which can combine knowledge from a pool of domains in order to create a solution for a new domain. ( ... The project involved developing an architecture to support incremental dialogue, and advancing

27 Jul 2020: SPEAKER DIARISATION FOR BROADCAST NEWS. S. E. Tranter and D. A. ... A new clustering procedure and BIC-based stopping criterion for the CUED system is introduced which improves both performance and robustness to changes in segmentation.

7 Oct 2009: Unsupervised Training for Mandarin Broadcast News and Conversation Transcription. ... Progress in the CU-HTK Broadcast News Transcription System.

27 Jul 2020: We examine the image quality and ease of use of the new method with in vitro and in vivo experiments. ... The new method is easier to use than the current best alternative and so more reliably produces images of superior quality.

Research Opportunities in the Medical Imaging Group. We are always looking for new students with knowledge and interest in one or more of the following areas:.

In Acoustics, Speech and Signal Processing, New Orleans, USA (March) pages 4920-4924, 2017. ... A new look at filtering techniques for illumination invariance in automatic face recognition.

Trabia, Palermo (Sicily), May 26-29, 1998. Co-Chair of Royal Society Discussion Meeting on New Geometric Techniques in Computer Vision,.