Search

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: All the new schemes make use of state information, specifically which state each of the components belongs to. ... These new approach are compared with the standard GS scheme on a large vocabulary speech recognition task.

27 Jul 2020: B. T. Logan and A. J. Robinson. Dec 1996. This paper describes a new algorithm to enhance and recognise noisy speech when only the noisy signal is available. ... These likelihoods are used to weight each observation to form a new estimate of the noise

27 Jul 2020: Abstract for tham_ml94. To appear in: Machine Learning: Proceedings of the Eleventh International Conference (ML'94), New Brunswick, New Jersey, USA.

27 Jul 2020: In order to extract this 3D model the scene is represented as a collection of layers and a new method for layer extraction is described. ... The new segmentation method differs from previous methods in that it uses a specific prior model for layer shape.

27 Jul 2020: However, the main drawbacks are (1) new views cannot be added easily at a later time, and (2) part of the structure will always remain invisible under circular motion. ... The 3D models thus obtained can be refined incrementally by adding new arbitrary

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: costs. By analysis of a set of existing classifiers using a receiver operating characteristic (ROC) curve, a set of new realisable classifiers may be obtained by a principled random combination of ... This new system is shown to produce the MRROC, and as

27 Jul 2020: In this paper, a new form of acoustic model is described called the Segmental Hidden Markov Model (SHMM) in which the effect of the Independence Assumption' on the observation likelihood is ... The new model is shown to provide better recognition

27 Jul 2020: Abstract for woodland_icassp97. Proceedings ICASSP'97. BROADCAST NEWS TRANSCRIPTION USING HTK. P.C. ... It includes a number of new features over previous HTK large vocabulary systems including decoder-guided segmentation, segment clustering, cache-based

27 Jul 2020: Abstract for blackburn_icnn95. Proc. ICNN 95. LEARNING NEW ARTICULATOR TRAJECTORIES FOR A SPEECH PRODUCTION MODEL USING ARTIFICIAL NEURAL NETWORKS. ... The techniques used to initialise and train the system are described, and preliminary results for the

27 Jul 2020: 3-D free-hand ultrasound is a new imaging technique which is rapidly finding clinical applications. ... This paper describes a new calibration technique, which takes only a few minutes to perform and produces more accurate and repeatable results than all

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: Consequently, new methods are required to allow users to pin-point specific items of interest in large data collections. ... In a baseline system, a new technique for wordspotting allows items matching an arbitrary expression of the information

27 Jul 2020: Abstract for hain_icassp01. Proc. ICASSP'01 (Vol I), Salt Lake City. NEW FEATURES IN THE CU-HTK SYSTEM FOR TRANSCRIPTION OF CONVERSATIONAL TELEPHONE SPEECH. ... This paper discusses new features integrated into the Cambridge University HTK (CU-HTK)

27 Jul 2020: A general system structure for 10 times real-time systems is proposed and two specific systems that have been built for Broadcast News (BN) and Conversational Telephone Speech (CTS) recognition are

27 Jul 2020: This paper introduces a new form of covariance matrix which allows a few full'' covariance matrices to be shared over many distributions, whilst each distribution maintains its own diagonal'' covariance matrix. ... The new form of covariance matrix is

27 Jul 2020: Abstract for johnson_riao00. Proceedings, RIAO 2000. AUDIO INDEXING AND RETRIEVAL OF COMPLETE BROADCAST NEWS SHOWS. ... April 2000. This paper describes a system for retrieving relevant portions of complete broadcast news shows starting with only the

27 Jul 2020: The broadcast news audio was transcribed using a 2-pass gender-dependent HTK speech recogniser which ran at 50 times real time and gave an overall word error rate of ... The paper also presents results on a new set of 60 queries with assessments for the

27 Jul 2020: The 500 hours of broadcast news audio was filtered using an automatic scheme for detecting commercials, and then transcribed using a 2-pass HTK speech recogniser which ran at 13 times

27 Jul 2020: Kok-Guan Lim and Richard W. Prager. July 1992. We present a new method using a Markov Random Field (MRF) to integrate edge and intensity based stereo algorithms.

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: news (BN) and conversational telephone speech (CTS) domains.

27 Jul 2020: A full-scale implementation is then described and tested on data from the 1996 Broadcast News database. ... A new criterion for evaluating the clusters is defined and shown to be a good indication of speaker split.

27 Jul 2020: THE APPLICABILITY OF LANGUAGE MODEL ADAPTATION FOR THE BROADCAST NEWS TASK. ... We will concentrate on cache-based and mixture-based models and their use on the Broadcast News task.

27 Jul 2020: A new system combination technique is presented that uses these confidence scores and the confusion networks and performs better than the well-known ROVER. |

27 Jul 2020: Furthermore, a new method for motion estimation from sequences of profiles is proposed.

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. |

27 Jul 2020: Woodland. March 1999. This paper describes the spoken document retrieval system that we have been developing and assesses its performance using automatic transcriptions of about 50 hours of broadcast news data. ... The recognition engine is based on the

27 Jul 2020: Finally, cross recogniser experiments again showed there is little performance degradation as WER increases and thus SDR now needs new challenges such as integration with video data. |

27 Jul 2020: The aim of this paper is to build on this progress by presenting a new analytical framework in which problem mappings can be evaluated without recourse to purely experimental means.

27 Jul 2020: Contact:Title A NEW LOOK AT FILTERING TECHNIQUES FOR ILLUMINATION INVARIANCE IN AUTOMATIC FACE RECOGNITION.

27 Jul 2020: The model parameters of a general speaker independent system are adapted to a new speaker using a transformation of the mean vectors based on linear regression. ... Results show that a 42% reduction in error from the speaker independent system can be

27 Jul 2020: The system downloads the audio track of British and American news broadcasts from the Internet once a day and adds them to its archive. ... The audio, which comes in RealAudio format, is first converted into standard uncompressed format from which a

27 Jul 2020: The projection matrices are used to recover partial 3D models of the scene and these can be used to visualise new viewpoints.

27 Jul 2020: Particular attention is paid to a new algorithm using Weighted Phase Separation, the performance of which is demonstrated in application to in vivo freehand strain imaging. ... The results support the theory that underlies the new algorithm, and more

27 Jul 2020: Cipolla. July 2001. This paper introduces a new probabilistic framework for Space Carving. ... This new framework avoids many of the difficulties associated with the original Space Carving algorithm.

27 Jul 2020: the system, a new distance measure between Gaussians based on overlap (which is used in the Roadmap algorithm), and an investigation of improvements to the Extended Baum-Welch formulae.

27 Jul 2020: Abstract for woodland_icassp98. Proc ICASSP'98, Seattle. EXPERIMENTS IN BROADCAST NEWS TRANSCRIPTION. ... Young. May 1998. This paper presents the recent development of the HTK broadcast news transcription system.

27 Jul 2020: Woodland, M.J.F. Gales, D. Pye & S.J. Young. April 1997. This paper describes our efforts in extending a large vocabulary speech recognition system to handle broadcast news transcription. ... It includes a number of new features compared to previous HTK

27 Jul 2020: A new scheme is described, which is a simple extension to the standard Parallel Model Combination (PMC) technique.

27 Jul 2020: This paper describes a new approach within this framework, uncertainty decoding. ... This approach is compared with the uncertainty decoding version of SPLICE, standard SPLICE, and a new form of front-end CMLLR.

27 Jul 2020: September 1996. 3-D ultrasound is a new medical imaging technique which can quickly and non-invasively deliver clinically useful renderings of internal structures.

27 Jul 2020: Unlike previous approaches which universally assume that new data comes in blocks representable by GMMs which are then merged with the current model estimate, our method works for the case when ... The current fit is updated with the assumption that the

27 Jul 2020: This is very important, since manual segmentation in 3D ultrasound is impractical for a reasonably sized training set, particular it has to be performed for each new class of shapes.

27 Jul 2020: NB New version created 4May98 with fixes for postscript bugs in original.