A Cache-Based Natural Language Model for Speech Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
A statistical approach to machine translation
Computational Linguistics
Class-based n-gram models of natural language
Computational Linguistics
Machine Learning
A maximum entropy approach to natural language processing
Computational Linguistics
The LIMSI Broadcast News transcription system
Speech Communication - Special issue on automatic transcription of broadcast news data
IJCNN '00 Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 2 - Volume 2
NAACL-Short '03 Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology: companion volume of the Proceedings of HLT-NAACL 2003--short papers - Volume 2
Training neural network language models on very large corpora
HLT '05 Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing
Continuous space language models for statistical machine translation
COLING-ACL '06 Proceedings of the COLING/ACL on Main conference poster sessions
New directions in connectionist language modeling
IWANN'03 Proceedings of the Artificial and natural neural networks 7th international conference on Computational methods in neural modeling - Volume 1
Sequential neural text compression
IEEE Transactions on Neural Networks
Speech Processing for Audio Indexing
GoTAL '08 Proceedings of the 6th international conference on Advances in Natural Language Processing
Fast Evaluation of Connectionist Language Models
IWANN '09 Proceedings of the 10th International Work-Conference on Artificial Neural Networks: Part I: Bio-Inspired Systems: Computational and Ambient Intelligence
Building a statistical machine translation system for French using the Europarl corpus
StatMT '07 Proceedings of the Second Workshop on Statistical Machine Translation
LIMSI's statistical translation systems for WMT'08
StatMT '08 Proceedings of the Third Workshop on Statistical Machine Translation
First steps towards a general purpose French/English statistical machine translation system
StatMT '08 Proceedings of the Third Workshop on Statistical Machine Translation
Automatic Speech-to-Text Transcription in Arabic
ACM Transactions on Asian Language Information Processing (TALIP)
Recursive n-gram hashing is pairwise independent, at best
Computer Speech and Language
LIUM SMT machine translation system for WMT 2010
WMT '10 Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR
UCH-UPV English: Spanish system for WMT10
WMT '10 Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR
Training continuous space language models: some practical issues
EMNLP '10 Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing
WMT '11 Proceedings of the Sixth Workshop on Statistical Machine Translation
LIUM's SMT machine translation systems for WMT 2011
WMT '11 Proceedings of the Sixth Workshop on Statistical Machine Translation
CEU-UPV English-Spanish system for WMT11
WMT '11 Proceedings of the Sixth Workshop on Statistical Machine Translation
Statistical machine translation with local language models
EMNLP '11 Proceedings of the Conference on Empirical Methods in Natural Language Processing
A fast re-scoring strategy to capture long-distance dependencies
EMNLP '11 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Efficient subsampling for training complex language models
EMNLP '11 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Use of contexts in language model interpolation and adaptation
Computer Speech and Language
Continuous space translation models with neural networks
NAACL HLT '12 Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Measuring the influence of long range dependencies with neural network language models
WLM '12 Proceedings of the NAACL-HLT 2012 Workshop: Will We Ever Really Replace the N-gram Model? On the Future of Language Modeling for HLT
Large, pruned or continuous space language models on a GPU for statistical machine translation
WLM '12 Proceedings of the NAACL-HLT 2012 Workshop: Will We Ever Really Replace the N-gram Model? On the Future of Language Modeling for HLT
Deep neural network language models
WLM '12 Proceedings of the NAACL-HLT 2012 Workshop: Will We Ever Really Replace the N-gram Model? On the Future of Language Modeling for HLT
A challenge set for advancing language modeling
WLM '12 Proceedings of the NAACL-HLT 2012 Workshop: Will We Ever Really Replace the N-gram Model? On the Future of Language Modeling for HLT
LIUM's SMT machine translation systems for WMT 2012
WMT '12 Proceedings of the Seventh Workshop on Statistical Machine Translation
Language model cross adaptation for LVCSR system combination
Computer Speech and Language
Neural network language models for off-line handwriting recognition
Pattern Recognition
IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP)
Hi-index | 0.00 |
This paper describes the use of a neural network language model for large vocabulary continuous speech recognition. The underlying idea of this approach is to attack the data sparseness problem by performing the language model probability estimation in a continuous space. Highly efficient learning algorithms are described that enable the use of training corpora of several hundred million words. It is also shown that this approach can be incorporated into a large vocabulary continuous speech recognizer using a lattice rescoring framework at a very low additional processing time. The neural network language model was thoroughly evaluated in a state-of-the-art large vocabulary continuous speech recognizer for several international benchmark tasks, in particular the Nist evaluations on broadcast news and conversational speech recognition. The new approach is compared to four-gram back-off language models trained with modified Kneser-Ney smoothing which has often been reported to be the best known smoothing method. Usually the neural network language model is interpolated with the back-off language model. In that way, consistent word error rate reductions for all considered tasks and languages were achieved, ranging from 0.4% to almost 1% absolute.