Search

27 Jul 2020: We show how the new algorithms outperform extended Kalman filter training and radial basis function networks on several problems.

27 Jul 2020: news from the 1997 TREC-7 spoken document retrieval track.

27 Jul 2020: NB New version created 22May98 with fixes for postscript bugs in original.

27 Jul 2020: Paul Smith, Tom Drummond, and Roberto Cipolla. Sept 1999. This paper presents a new theoretical framework for motion segmentation based on the motion of tracked region edges.

27 Jul 2020: We develop a new statistical theory to predict the improvement in signal to noise ratio with increased levels of compounding, and verify the predictions empirically.

27 Jul 2020: In this paper we present a new object recognition system named MLBoost which learns from multi-label data through boosting and improves on state-of-the-art multi-label annotation and

27 Jul 2020: The new Cambridge phantom and the conventional cross-wire phantom are shown to offer the best performance. ... The new functional method exploits the underlying shape of the ultrasound data to fill gaps and average overlapping data, without introducing

27 Jul 2020: S.E. Johnson and P.C. Woodland. December 1998. In this paper speaker clustering schemes are investigated in the context of improving unsupervised adaptation for broadcast news transcription.

27 Jul 2020: Contact:Title AUDIO INDEXING AND RETRIEVAL OF COMPLETE BROADCAST NEWS SHOWS. Abstract: johnson_riao00. ... Contact:Title SEGMENT GENERATION AND CLUSTERING IN THE HTK BROADCAST NEWS TRANSCRIPTION SYSTEM.

27 Jul 2020: This work, briefly summarized here, used stochastic decision trees trained on phonetic and linguistic features, and was applied to the DARPA North American Business News read- speech ASR task.

27 Jul 2020: Paul Smith, Tom Drummond, and Roberto Cipolla. June 2000. This paper presents a new Bayesian framework for layered motion segmentation, dividing the frames of an image sequence into foreground and background

27 Jul 2020: The criteria to add a new basis function to the model are based on the angle formed between a new basis function and the existing basis functions and also on the ... When a new basis function is not added the model parameters are adapted by the extended

27 Jul 2020: In current systems it is essential to be able to rapidly adapt the acoustic models to a particular speaker or new acoustic environment.

27 Jul 2020: One published method of choosing a model within this space, Maximal Likelihood Eigenvoice Decomposition, is presented and compared with a new method, Weighted Projection.

27 Jul 2020: Further, a new technique, the Median Flow Filter, is introduced. This detects outliers by assuming that the image motion is locally similar.

27 Jul 2020: J. Shotton, J. Winn, C. Rother, and A. Criminisi. 2006. This paper proposes a new approach to learning a discriminative model of object classes, incorporating appearance, shape and context information

27 Jul 2020: In this paper we propose a new scheme to numerically represent and evolve surfaces in 3D. ... With the new scheme, efficiency and accuracy are further improved. For the representation, space is partitioned into tetrahedra and finite elements are used to

27 Jul 2020: An illustration of a found-speech task is maintaining an archive of audio, for example, transmitted broadcast news. ... Broadcast News transcription is also complicated by the presence of different audio conditions.

27 Jul 2020: In chapter 4 we investigate the growth function and VC dimension for general and specific Phi-networks, obtaining several new results. ... In chapter 5 we derive new necessary and sufficient conditions on the number of training examples required when

27 Jul 2020: The effectiveness of these techniques is demonstrated on the broadcast news and the conversational telephone speech corpora where improvements both in terms of word error rate and normalised cross entropy were