Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ arXiv.org e-Print Ar...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
ZENODO
Conference object . 2019
License: CC BY
Data sources: Datacite
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
ZENODO
Conference object . 2019
License: CC BY
Data sources: ZENODO
https://doi.org/10.48550/arxiv...
Article . 2019
License: arXiv Non-Exclusive Distribution
Data sources: Datacite
versions View all 4 versions
addClaim

This Research product is the result of merged Research products in OpenAIRE.

You have already added 0 works in your ORCID record related to the merged Research product.
addClaim

This Research product is the result of merged Research products in OpenAIRE.

You have already added 0 works in your ORCID record related to the merged Research product.

Breaking the Data Barrier: Towards Robust Speech Translation via Adversarial Stability Training

Authors: Cheng, Qiao; Fang, Meiyuan; Han, Yaqian; Huang, Jin; Duan, Yitao;

Breaking the Data Barrier: Towards Robust Speech Translation via Adversarial Stability Training

Abstract

In a pipeline speech translation system, automatic speech recognition (ASR) system will transmit errors in recognition to the downstream machine translation (MT) system. A standard machine translation system is usually trained on parallel corpus composed of clean text and will perform poorly on text with recognition noise, a gap well known in speech translation community. In this paper, we propose a training architecture which aims at making a neural machine translation model more robust against speech recognition errors. Our approach addresses the encoder and the decoder simultaneously using adversarial learning and data augmentation, respectively. Experimental results on IWSLT2018 speech translation task show that our approach can bridge the gap between the ASR output and the MT input, outperforms the baseline by up to 2.83 BLEU on noisy ASR output, while maintaining close performance on clean text.

Comment: Accepted at the 16th International Workshop on Spoken Language Translation (IWSLT 2019)

Keywords

FOS: Computer and information sciences, Computer Science - Computation and Language, Audio and Speech Processing (eess.AS), FOS: Electrical engineering, electronic engineering, information engineering, Computation and Language (cs.CL), Electrical Engineering and Systems Science - Audio and Speech Processing

27 references, page 1 of 3

[1] R. J. Weiss, J. Chorowski, N. Jaitly, Y. Wu, and Z. Chen, “Sequence-to-sequence models can directly translate foreign speech,” Proc. Interspeech 2017, pp. 2625-2629, 2017.

[2] A. Bérard, O. Pietquin, L. Besacier, and C. Servan, “Listen and translate: A proof of concept for end-toend speech-to-text translation,” in NIPS Workshop on end-to-end learning for speech and audio processing, 2016. [OpenAIRE]

[3] S. Peitz, S. Wiesler, M. Nußbaum-Thom, and H. Ney, “Spoken language translation using automatically transcribed text in training,” in International Workshop on Spoken Language Translation (IWSLT) 2012, 2012. [OpenAIRE]

[4] M. Sperber, G. Neubig, J. Niehues, and A. Waibel, “Neural lattice-to-sequence models for uncertain inputs,” in Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, 2017, pp. 1380-1389.

[5] M. Post, G. Kumar, A. Lopez, D. Karakos, C. CallisonBurch, and S. Khudanpur, “Improved speech-to-text translation with the fisher and callhome spanishenglish speech translation corpus,” in Proc. IWSLT, 2013.

[6] N. Jan, R. Cattoni, S. Sebastian, M. Cettolo, M. Turchi, and M. Federico, “The iwslt 2018 evaluation campaign,” in International Workshop on Spoken Language Translation, 2018, pp. 2-6.

[7] X. Li, H. Xue, W. Chen, Y. Liu, Y. Feng, and Q. Liu, “Improving the robustness of speech translation,” arXiv preprint arXiv:1811.00728, 2018.

[8] M. Sperber, J. Niehues, and A. Waibel, “Toward robust neural machine translation for noisy input sequences,” in International Workshop on Spoken Language Translation (IWSLT), Tokyo, Japan, 2017.

[9] A. Bérard, L. Besacier, A. C. Kocabiyikoglu, and O. Pietquin, “End-to-end automatic speech translation of audiobooks,” in 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2018, pp. 6224-6228.

[10] D. Serdyuk, Y. Wang, C. Fuegen, A. Kumar, B. Liu, and Y. Bengio, “Towards end-to-end spoken language understanding,” in 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2018, pp. 5754-5758.

  • BIP!
    Impact byBIP!
    citations
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    6
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Top 10%
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
  • citations
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    6
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Top 10%
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
    Powered byBIP!BIP!
Powered by OpenAIRE graph
Found an issue? Give us feedback
citations
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
6
Top 10%
Average
Average
moresidebar

Do the share buttons not appear? Please make sure, any blocking addon is disabled, and then reload the page.