Connectionist speech recognition of broadcast news (2002)

by A Robinson, G Cook, D Ellis, E Fosler-Lussier, S Renals, D Williams
Venue:Speech Communications
Add To MetaCart
Results 1 - 10 of 38

Context-Dependent Pre-trained Deep Neural Networks for Large Vocabulary Speech Recognition

by George E. Dahl, Dong Yu, Li Deng, Alex Acero - IEEE TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING , 2012
"... We propose a novel context-dependent (CD) model for large vocabulary speech recognition (LVSR) that leverages recent advances in using deep belief networks for phone recognition. We describe a pretrained deep neural network hidden Markov model (DNN-HMM) hybrid architecture that trains the DNN to pr ..."
Abstract - Cited by 254 (50 self) - Add to MetaCart
We propose a novel context-dependent (CD) model for large vocabulary speech recognition (LVSR) that leverages recent advances in using deep belief networks for phone recognition. We describe a pretrained deep neural network hidden Markov model (DNN-HMM) hybrid architecture that trains the DNN to produce a distribution over senones (tied triphone states) as its output. The deep belief network pre-training algorithm is a robust and often helpful way to initialize deep neural networks generatively that can aid in optimization and reduce generalization error. We illustrate the key components of our model, describe the procedure for applying CD-DNN-HMMs to LVSR, and analyze the effects of various modeling choices on performance. Experiments on a challenging business search dataset demonstrate that CD-DNN-HMMs can significantly outperform the conventional context-dependent Gaussian mixture model (GMM)-HMMs, with an absolute sentence accuracy improvement of 5.8 % and 9.2 % (or relative error reduction of 16.0 % and 23.2%) over the CD-GMM-HMMs trained using the minimum phone error rate (MPE) and maximum likelihood (ML) criteria, respectively.

Punctuation annotation using statistical prosody models

by Heidi Christensen, Yoshihiko Gotoh, Steve Renals - in Proc. ISCA Workshop on Prosody in Speech Recognition and Understanding , 2001
"... This paper is about the development of statistical models of prosodic features to generate linguistic meta-data for spoken language. In particular, we are concerned with automatically punctuating the output of a broadcast news speech recogniser. We present a statistical finite state model that combi ..."
Abstract - Cited by 40 (3 self) - Add to MetaCart
This paper is about the development of statistical models of prosodic features to generate linguistic meta-data for spoken language. In particular, we are concerned with automatically punctuating the output of a broadcast news speech recogniser. We present a statistical finite state model that combines prosodic, linguistic and punctuation class features. Experimental results are presented using the Hub–4 Broadcast News corpus, and in the light of our results we discuss the issue of a suitable method of evaluating the present task. 1.
(Show Context)

Indexing and Retrieval of Broadcast News

by Steve Renals, Dave Abberley, David Kirby, Tony Robinson - Speech Communication , 2000
"... This paper describes a spoken document retrieval (SDR) system for British and North American Broadcast News. The system is based on a connectionist large vocabulary speech recognizer and a probabilistic information retrieval system. We discuss the development of a realtime Broadcast News speech r ..."
Abstract - Cited by 33 (7 self) - Add to MetaCart
This paper describes a spoken document retrieval (SDR) system for British and North American Broadcast News. The system is based on a connectionist large vocabulary speech recognizer and a probabilistic information retrieval system. We discuss the development of a realtime Broadcast News speech recognizer, and its integration into an SDR system. Two advances were made for this task: automatic segmentation and statistical query expansion using a secondary corpus. Precision and recall results using the Text Retrieval Conference (TREC) SDR evaluation infrastructure are reported throughout the paper, and we discuss the application of these developments to a large scale SDR task based on an archive of British English broadcast news. Keywords: Spoken Document Retrieval; Information Retrieval; Broadcast Speech; Large Vocabulary Speech Recognition. 1 Introduction Retrieval of audio segments according to their content is a challenging and significant problem. It has been estimated th...

Framewise phone classification using support vector machines

by Jesper Salomon - In Proceedings of the Seventh International Conference on Spoken Language Processing , 2002
"... We describe the use of Support Vector Machines for phonetic classification on the TIMIT corpus. Unlike previous work, in which entire phonemes are classified, our system operates in a framewise manner and is intended for use as the front-end of a hybrid system similar to ABBOT. We therefore avoid th ..."
Abstract - Cited by 24 (1 self) - Add to MetaCart
We describe the use of Support Vector Machines for phonetic classification on the TIMIT corpus. Unlike previous work, in which entire phonemes are classified, our system operates in a framewise manner and is intended for use as the front-end of a hybrid system similar to ABBOT. We therefore avoid the problems of classifying variable-length vectors. Our frame-level phone classification accuracy on the complete TIMIT test set is competitive with other results from the literature. In addition, we address the serious problem of scaling Support Vector Machines by using the Kernel Fisher Discriminant. 1.
(Show Context)

Automatic summarization of voicemail messages using lexical and prosodic features

by Konstantinos Koumpis, Steve Renals - ACM Transactions on Speech and Language Processing , 2005
"... This aticle presents trainable methods for extracting principal content words from voicemail messages. The short text summaries generated are suitable for mobile messaging applications. The system uses a set of classifiers to identify the summary words with each word described by a vector of lexical ..."
Abstract - Cited by 22 (3 self) - Add to MetaCart
This aticle presents trainable methods for extracting principal content words from voicemail messages. The short text summaries generated are suitable for mobile messaging applications. The system uses a set of classifiers to identify the summary words with each word described by a vector of lexical and prosodic features. We use an ROC-based algorithm, Parcel, to select input features (and classifiers). We have performed a series of objective and subjective evaluations using unseen data from two different speech recognition systems as well as human transcriptions of voicemail speech.

Transcription And Summarization Of Voicemail Speech

by Konstantinos Koumpis, Steve Renals - Proc. ICSLP , 2000
"... This paper describes the development of a system to transcribe and summarize voicemail messages. The results of the research presented in this paper are two-fold. First, a hybrid connectionist approach to the Voicemail transcription task shows that competitive performance can be achieved using a con ..."
Abstract - Cited by 19 (8 self) - Add to MetaCart
This paper describes the development of a system to transcribe and summarize voicemail messages. The results of the research presented in this paper are two-fold. First, a hybrid connectionist approach to the Voicemail transcription task shows that competitive performance can be achieved using a context-independent system with fewer parameters than those based on mixtures of Gaussian likelihoods. Second, an effective and robust combination of statistical with prior knowledge sources for term weighting is used to extract information from the decoder's output in order to deliver summaries to the message recipients via a GSM Short Message Service (SMS) gateway. 1. INTRODUCTION As the emphasis in cellular networks changes from voice-only communication to a rich combination of content based applications and services, speech recognition can provide access to several types of information through a number of portable solutions, including mobile phones and personal digital assistants. This pa...
(Show Context)

On using MLP features in LVCSR

by Qifeng Zhu, Barry Chen, Nelson Morgan, Andreas Stolcke - Proc. ICSLP, Jeju, Korea , 2004
"... One of the major research thrusts in the speech group at ICSI is to use Multi-Layer Perceptron (MLP) based features in automatic speech recognition (ASR). This paper presents a study of three aspects of this effort: 1) the properties of the MLP features which make them useful, 2) incorporating MLP f ..."
Abstract - Cited by 17 (2 self) - Add to MetaCart
One of the major research thrusts in the speech group at ICSI is to use Multi-Layer Perceptron (MLP) based features in automatic speech recognition (ASR). This paper presents a study of three aspects of this effort: 1) the properties of the MLP features which make them useful, 2) incorporating MLP features together with PLP features in ASR, and 3) possible redundancy between MLP features and more conventional system refinements such as discriminative training and system combination. The paper shows that MLP transformations yield variables that have regular distributions, which can be further modified by using logarithm to make the distribution easier to model by a Gaussian-HMM. Two or more vectors of these features can easily be combined without increasing the feature dimension. Recognition results show that MLP features can significantly improve recognition performance in large vocabulary continuous speech recognition (LVCSR) tasks for the NIST 2001 Hub-5 evaluation set with models trained on the Switchboard Corpus, even when discriminative training and system combination are used. 1.
(Show Context)

MULTI-LEVEL ADAPTIVE NETWORKS IN TANDEM AND HYBRID ASR SYSTEMS

by Peter Bell, Pawel Swietojanski, Steve Renals
"... In this paper we investigate the use of Multi-level adaptive networks (MLAN) to incorporate out-of-domain data when training large vocabulary speech recognition systems. In a set of experiments on multi-genre broadcast data and on TED lecture recordings we present results using of out-of-domain feat ..."
Abstract - Cited by 16 (12 self) - Add to MetaCart
In this paper we investigate the use of Multi-level adaptive networks (MLAN) to incorporate out-of-domain data when training large vocabulary speech recognition systems. In a set of experiments on multi-genre broadcast data and on TED lecture recordings we present results using of out-of-domain features in a hybrid DNN system and explore tandem systems using a variety of input acoustic features. Our experiments indicate using the MLAN approach in both hybrid and tandem systems results in consistent reductions in word error rate of 5–10 % relative. Index Terms — deep neural networks, tandem, hybrid, MLAN, TED, BBC
(Show Context)

Information Extraction from Broadcast News

by Yoshihiko Gotoh, Steve Renals - Philosophical Transactions of the Royal Society of London, Series A , 2000
"... This paper discusses the development of trainable statistical models for extracting content from television and radio news broadcasts. In particular we concentrate on statistical finite state models for identifying proper names and other named entities in broadcast speech. Two models are presented: ..."
Abstract - Cited by 15 (7 self) - Add to MetaCart
This paper discusses the development of trainable statistical models for extracting content from television and radio news broadcasts. In particular we concentrate on statistical finite state models for identifying proper names and other named entities in broadcast speech. Two models are presented: the first models name class information as a word attribute; the second explicitly models both word-word and class-class transitions. A common n-gram based formulation is used for both models. The task of named entity identification is characterized by relatively sparse training data and issues related to smoothing are discussed. Experiments are reported using the DARPA/NIST Hub--4E evaluation for North American Broadcast News.
(Show Context)

Compound decomposition in Dutch large vocabulary speech recognition

by Roeland Ordelman , Arjan van Hessen, Franciska de Jong - IN PROCEEDINGS OF EUROSPEECH 2003, GENEVE , 2003
"... This paper addresses compound splitting for Dutch in the context of broadcast news transcription. Language models were created using original text versions and text versions that were decomposed using a data-driven compound splitting algorithm. Language model performances were compared in terms of o ..."
Abstract - Cited by 13 (0 self) - Add to MetaCart
This paper addresses compound splitting for Dutch in the context of broadcast news transcription. Language models were created using original text versions and text versions that were decomposed using a data-driven compound splitting algorithm. Language model performances were compared in terms of outof -vocabulary rates and word error rates in a real-world broadcast news transcription task. It was concluded that compound splitting does improve ASR performance. Best results were obtained when frequent compounds were not decomposed.