• Türkçe
    • English
  • English 
    • Türkçe
    • English
  • Login
View Item 
  •   DSpace@MEF
  • Fakülteler
  • Mühendislik Fakültesi
  • Elektrik Elektronik Mühendisliği | Electrical and Electronics Engineering
  • MF, EEM, Bildiri ve Sunum Koleksiyonu
  • View Item
  •   DSpace@MEF
  • Fakülteler
  • Mühendislik Fakültesi
  • Elektrik Elektronik Mühendisliği | Electrical and Electronics Engineering
  • MF, EEM, Bildiri ve Sunum Koleksiyonu
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.
Advanced Search

Bidirectional recurrent neural network language models for automatic speech recognition

Access

info:eu-repo/semantics/closedAccess

Date

2015

Author

Arısoy, Ebru
Sethy, Abhinav
Ramabhadran, Bhuvana
Chen, Stanley

Metadata

Show full item record

Citation

Arisoy, E., Sethy, A., Ramabhadran, B., Chen, S., (APR 19-24, 2015 ). Bidirectional recurrent neural network language models for automatic speech recognition. 40th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) Location: Brisbane, AUSTRALIA. 5421-5425.

Abstract

Recurrent neural network language models have enjoyed great success in speech recognition, partially due to their ability to model longer-distance context than word n-gram models. In recurrent neural networks (RNNs), contextual information from past inputs is modeled with the help of recurrent connections at the hidden layer, while Long Short-Term Memory (LSTM) neural networks are RNNs that contain units that can store values for arbitrary amounts of time. While conventional unidirectional networks predict outputs from only past inputs, one can build bidirectional networks that also condition on future inputs. In this paper, we propose applying bidirectional RNNs and LSTM neural networks to language modeling for speech recognition. We discuss issues that arise when utilizing bidirectional models for speech, and compare unidirectional and bidirectional models on an English Broadcast News transcription task. We find that bidirectional RNNs significantly outperform unidirectional RNNs, but bidirectional LSTMs do not provide any further gain over their unidirectional counterparts.

Source

Conference: 40th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) Location: Brisbane, AUSTRALIA Date: APR 19-24, 2015

URI

https://hdl.handle.net/20.500.11779/705

Collections

  • Araştırma Çıktıları, WOS İndeksli Yayınlar Koleksiyonu [470]
  • MF, EEM, Bildiri ve Sunum Koleksiyonu [28]



DSpace software copyright © 2002-2015  DuraSpace
Contact Us | Send Feedback
Theme by 
@mire NV
 

 




| Instruction | Guide | Contact |

DSpace@MEF

by OpenAIRE

sherpa/romeo

Browse

All of DSpaceCommunities & CollectionsBy Issue DateAuthorsInstitution AuthorTitlesORCIDSubjectsTypeLanguageDepartmentCategoryPublisherAccess TypeThis CollectionBy Issue DateAuthorsInstitution AuthorTitlesORCIDSubjectsTypeLanguageDepartmentCategoryPublisherAccess Type

My Account

LoginRegister

Statistics

View Google Analytics Statistics

DSpace software copyright © 2002-2015  DuraSpace
Contact Us | Send Feedback
Theme by 
@mire NV
 

 


|| Guide|| Instruction || Library || MEF University || OAI-PMH ||

MEF University Library, İstanbul, Turkey
If you find any errors in content please report us

Creative Commons License
MEF University Institutional Repository is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 4.0 Unported License..

DSpace@MEF:


DSpace 6.2

tarafından İdeal DSpace hizmetleri çerçevesinde özelleştirilerek kurulmuştur.