Results 1 - 10 of 18

Automatic Segmentation, Classification and Clustering of Broadcast News Audio

by Matthew A. Siegler, Uday Jain, Bhiksha Raj, Richard M. Stern - Proc. DARPA Speech Recognition Workshop , 1997
"... Automatic recognition of broadcast feeds from radio and television sources has been gaining importance recently, especially with the success of systems such as the CMU Informedia system [1]. In this work we describe the problems faced in adapting a system built to recognize one utterance at a time t ..."
Abstract - Cited by 150 (11 self) - Add to MetaCart
are evaluated through comparisons between the Partitioned and Unpartitioned components of the 1996 ARPA Hub 4 evaluation test set. 1.

The hub and spoke paradigm for CSR evaluation

by Francis Kubala, Jerome Bellegarda, Jordan Cohen, David Pallett, Doug Paul, Mike Phillips, Raja Rajasekaran, Fred Richardson, Michael Riley, Roni Rosenfeld, Bob Roth, Mitch Weintraub - In Proceedings of the DARPA Spoken Language Technology Workshop , 1994
"... In this paper, we introduce the new paradigm used in the most re-cent ARPA-sponsored Continuous Speech Recognition (CSR) eval-uation and then discuss the important features of the test design. The 1993 CSR evaluation was organized in a novel fashion in an attempt to accomodate research over a broad ..."
Abstract - Cited by 11 (2 self) - Add to MetaCart
In this paper, we introduce the new paradigm used in the most re-cent ARPA-sponsored Continuous Speech Recognition (CSR) eval-uation and then discuss the important features of the test design. The 1993 CSR evaluation was organized in a novel fashion in an attempt to accomodate research over a broad

The LIMSI 1995 Hub3 System

by J.L. Gauvain, L. Lamel, G. Adda, D. Matrouf
"... In this paper we report on the LIMSI recognizer evaluated in the ARPA 1995 North American Business (NAB) News Hub 3 benchmark test. The LIMSI recognizer is an HMM-based system with Gaussian mixture. Decoding is carried out in multiple forward acoustic passes, where more refined acoustic and language ..."
Abstract - Add to MetaCart
In this paper we report on the LIMSI recognizer evaluated in the ARPA 1995 North American Business (NAB) News Hub 3 benchmark test. The LIMSI recognizer is an HMM-based system with Gaussian mixture. Decoding is carried out in multiple forward acoustic passes, where more refined acoustic

Developments in Continuous Speech Dictation Using the ARPA WSJ Task

by J. L.Gauvain, L. Lamel, M. Adda-decker - In ICASSP -- Proc. of the IEEE International Conference on Acoustics, Speech and Signal Processing , 1995
"... In this paper we report on our recent development work in large vocabulary,American English continuous speech dictation. We have experimented with (1) alternative analyses for the acoustic front end, (2) the use of an enlarged vocabulary so as to reduce the number of errors due to out-of-vocabulary ..."
Abstract - Add to MetaCart
-of-vocabulary words, (3) extensions to the lexical representation, (4) the use of additional acoustic training data, and (5) modification of the acoustic models for telephone speech. The recognizer was evaluated on Hubs 1 and 2 of the fall 1994 ARPA NAB CSR Hub and Spoke Benchmark test. Experimental results

Developments in Continuous Speech Dictation using the 1995 ARPA NAB News Task

by J.L. Gauvain, L. Lamel, G. Adda, D. Matrouf , 1996
"... In this paper we report on the LIMSI recognizer evaluated in the ARPA 1995 North American Business (NAB) News benchmark test. In contrast to previous evaluations, the new Hub 3 test aims at improving basic SI, CSR performance on unlimitedvocabulary read speech recorded under more varied acoustical c ..."
Abstract - Cited by 2 (0 self) - Add to MetaCart
In this paper we report on the LIMSI recognizer evaluated in the ARPA 1995 North American Business (NAB) News benchmark test. In contrast to previous evaluations, the new Hub 3 test aims at improving basic SI, CSR performance on unlimitedvocabulary read speech recorded under more varied acoustical

Transcription Of Broadcast Television And Radio News: The 1996 Abbot System

by G. D. Cook, Cook Kershaw, J. D. M. Christie, A. J. Robinson, Trumpington Street - In DARPA Speech Recognition Workshop , 1997
"... ABBOT is a hybrid connectionist-HMM large vocabulary continuous speech recognition system developed at the Cambridge University Engineering Department. This uses a recurrent neural network acoustic model to map acoustic features into posterior phone probabilities. These posterior probabilities are t ..."
Abstract - Cited by 18 (4 self) - Add to MetaCart
are then converted to scaled likelihoods and used as observation likelihoods for phone HMMs [1, 2]. This paper describes the development of the CUCON system which participated in the 1996 ARPA Hub 4 Evaluations. The system is based on ABBOT. The Hub 4 Evaluation task involves the transcription of broadcast

The 1995 Abbot Lvcsr System For Multiple Unknown Microphones

by Dan Kershaw , Tony Robinson, Steve Renals - IN INT. CONF. IN SPOKEN LANGUAGE PROCESSING , 1996
"... ABBOT is the hybrid connectionist-hidden Markov model largevocabulary speech recognition system developed at Cambridge University. In this system, a recurrent network maps each acoustic vector to an estimate of the posterior probabilities of the phone classes, which are used as observation probabili ..."
Abstract - Cited by 9 (6 self) - Add to MetaCart
probabilities within an HMM. This paper describes the system which participated in the November 1995 ARPA Hub-3 Multiple Unknown Microphones (MUM) evaluation of continuous speech recognition systems, under the guise of the CU-CON system. The emphasis of the paper is on the changes made to the 1994 ABBOT system

THE 1995 ABBOT LVCSR SYSTEM FOR MULTIPLE UNKNOWN MICROPHONES

by Dan Kershawt, Tony Robinsont, Steve Renal
"... ABBOT is the hybrid connectionist-hidden Markov model largevocabulary speech recognition system developed at Cambridge University. In this system, a recurrent network maps each acoustic vector io an estimate of the posterior probabilities of the phone classes, which are used as observation probabili ..."
Abstract - Add to MetaCart
probabilities within an HMM. This paper describes the system which participated in the November 1995 ARPA Hub-3 Multiple Unknown Microphones (MUM) evaluation of continuous speech recognition systems, under the guise of the CU-CON system. The emphasis of the paper is on the changes made to the 1994 ABBOT system

Transcribing Broadcast News: The LIMSI Nov96 Hub4 System

by Gauvain Adda Lamel, J. L. Gauvain, G. Adda, L. Lamel, M. Adda-decker - In Proc. of DARPA Speech Recognition Workshop , 1997
"... In this paper we report on the LIMSI Nov96 Hub4 system for transcription of broadcast news shows. We describe the development work in moving from laboratory read speech data to realworld speech data in order to build a system for the ARPA Nov96 evaluation. Two main problems were addressed to deal wi ..."
Abstract - Cited by 1 (0 self) - Add to MetaCart
In this paper we report on the LIMSI Nov96 Hub4 system for transcription of broadcast news shows. We describe the development work in moving from laboratory read speech data to realworld speech data in order to build a system for the ARPA Nov96 evaluation. Two main problems were addressed to deal

Speaker Adaptation by Correlation (ABC)

by Scott Shaobing Chen, Peter DeSouza , 1997
"... This paper describes a new rapid speaker adaptation algorithm using a small amount of adaptation data. This algorithm, termed adaptation by correlation #ABC#, exploits the intrinsic correlation among speech units to update the speech models. The algorithm updates the means of each Gaussian based on ..."
Abstract - Cited by 9 (0 self) - Add to MetaCart
on its correlation with means of the Gaussians which are observed in the adaptation data; the updating formula is derived from the theory of least squares. Our experiments on the ARPA NAB-94 evaluation #Eval-94# and the ARPA Hub4-96 #Hub4-96# tasks indicate that ABC seems more stable than MLLR when
Results 1 - 10 of 18