Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translation

This paper proposes a first attempt to build an end-to-end speech-to-text translation system, which does not use source language text during learning or decoding. Relaxing the need for source language transcription would drastically change the data collection methodology in speech translation, especially in under-resourced scenarios.

cs.CL Computer Science Linguistics

Paper

References (16)

01An Unsupervised Probability Model for Speech-to-Translation Alignment of Low-Resource LanguagesAntonios Anastasopoulos, David Chiang, Long Duong2016 · Conference on Empirical Methods in Natural Language Processing · 28 citations In Library

02Advances in all-neural speech recognitionG. Zweig, Chengzhu Yu, J. Droppo et al.2016 · IEEE International Conference on Acoustics, Speech, and Signal Processing · 96 citations In Library

03Preliminary Experiments on Unsupervised Word Discovery in MboshiPierre Godard, G. Adda, M. Adda-Decker et al.2016 · Interspeech · 18 citations

04An Attentional Model for Speech Translation Without TranscriptionLong Duong, Antonios Anastasopoulos, David Chiang et al.2016 · North American Chapter of the Association for Computational Linguistics · 156 citations

05Multi-Source Neural TranslationBarret Zoph, Kevin Knight2016 · North American Chapter of the Association for Computational Linguistics · 334 citations In Library

06Multi-task Sequence to Sequence LearningMinh-Thang Luong, Quoc V. Le, I. Sutskever et al.2015 · International Conference on Learning Representations · 837 citations In Library

07Listen, attend and spell: A neural network for large vocabulary conversational speech recognitionWilliam Chan, N. Jaitly, Quoc V. Le et al.2015 · IEEE International Conference on Acoustics, Speech, and Signal Processing · 2.5k citations In Library

08Attention-Based Models for Speech RecognitionJ. Chorowski, Dzmitry Bahdanau, Dmitriy Serdyuk et al.2015 · Neural Information Processing Systems · 2.8k citations In Library

09Grammar as a Foreign LanguageO. Vinyals, Lukasz Kaiser, Terry Koo et al.2014 · Neural Information Processing Systems · 942 citations In Library

10Adam: A Method for Stochastic OptimizationDiederik P. Kingma, Jimmy Ba2014 · International Conference on Learning Representations · 169k citations In Library

11Sequence to Sequence Learning with Neural NetworksI. Sutskever, O. Vinyals, Quoc V. Le2014 · Neural Information Processing Systems · 22k citations In Library

12Recurrent Neural Network RegularizationWojciech Zaremba, I. Sutskever, O. Vinyals2014 · arXiv.org · 3.0k citations In Library

Scroll for more · 4 remaining

Similar papers

Towards End-to-end Speech-to-text Translation with Two-pass DecodingTzu-Wei Sung, Jun-You Liu, Hung-yi Lee et al.2019 · IEEE International Conference on Acoustics, Speech, and Signal Processing · 32 citations In Library

Tutorial Proposal: End-to-End Speech TranslationJan Niehues, Elizabeth Salesky, Marco Turchi et al.2021 · Conference of the European Chapter of the Association for Computational Linguistics · 2 citations In Library

End-to-End Automatic Speech Translation of AudiobooksAlexandre Berard, L. Besacier, A. Kocabiyikoglu et al.2018 · IEEE International Conference on Acoustics, Speech, and Signal Processing · 208 citations In Library

Towards Unsupervised Speech-to-Text TranslationYu-An Chung, W. Weng, Schrasing Tong et al.2018 · IEEE International Conference on Acoustics, Speech, and Signal Processing · 45 citations In Library

Revisiting End-to-End Speech-to-Text Translation From ScratchBiao Zhang, Barry Haddow, Rico Sennrich2022 · arXiv (Cornell University) · 46 citations In Library

End-to-End Speech Translation With Transcoding by Multi-Task Learning for Distant Language PairsTakatomo Kano, Sakriani Sakti, Satoshi Nakamura2020 · IEEE/ACM Transactions on Audio Speech and Language Processing · 36 citations In Library

Speech Translation and the End-to-End Promise: Taking Stock of Where We AreMatthias Sperber, Matthias Paulik2020 In Library

Simple and Effective Unsupervised Speech TranslationChanghan Wang, Hirofumi Inaguma, Peng‐Jen Chen et al.2022 · arXiv (Cornell University) · 20 citations In Library

Long-Form End-to-End Speech Translation via Latent Alignment SegmentationPeter Polák, Ondřej Bojar2023 · arXiv (Cornell University) In Library

AlloST: Low-resource Speech Translation without Source TranscriptionYao-Fei Cheng, Hung-Shin Lee, Hsin‐Min Wang2021 · arXiv (Cornell University) · 10 citations In Library

Source of record

arXiv

44B

Welcome.

This panel sticks with you. Pick anything below and it opens right beside it, so you can dig through 60,000-plus records without ever losing your spot here.

Travel 44B

LibraryPapers, policy, standards, statute LabsEvery organization building AI ModelsIntelligence, price, and speed BenchmarksThe evaluation catalog IncidentsAI failures and harms SearchOne field across everything DashboardThe state of AI accountability in NY 44B RegistryThe Art. 44-B compliance portal