%0 Generic %1 berard2016listen %A Berard, Alexandre %A Pietquin, Olivier %A Servan, Christophe %A Besacier, Laurent %D 2016 %K mt speech %T Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translation %U http://arxiv.org/abs/1612.01744 %X This paper proposes a first attempt to build an end-to-end speech-to-text translation system, which does not use source language transcription during learning or decoding. We propose a model for direct speech-to-text translation, which gives promising results on a small French-English synthetic corpus. Relaxing the need for source language transcription would drastically change the data collection methodology in speech translation, especially in under-resourced scenarios. For instance, in the former project DARPA TRANSTAC (speech translation from spoken Arabic dialects), a large effort was devoted to the collection of speech transcripts (and a prerequisite to obtain transcripts was often a detailed transcription guide for languages with little standardized spelling). Now, if end-to-end approaches for speech-to-text translation are successful, one might consider collecting data by asking bilingual speakers to directly utter speech in the source language from target language text utterances. Such an approach has the advantage to be applicable to any unwritten (source) language.

@misc{berard2016listen, abstract = {This paper proposes a first attempt to build an end-to-end speech-to-text translation system, which does not use source language transcription during learning or decoding. We propose a model for direct speech-to-text translation, which gives promising results on a small French-English synthetic corpus. Relaxing the need for source language transcription would drastically change the data collection methodology in speech translation, especially in under-resourced scenarios. For instance, in the former project DARPA TRANSTAC (speech translation from spoken Arabic dialects), a large effort was devoted to the collection of speech transcripts (and a prerequisite to obtain transcripts was often a detailed transcription guide for languages with little standardized spelling). Now, if end-to-end approaches for speech-to-text translation are successful, one might consider collecting data by asking bilingual speakers to directly utter speech in the source language from target language text utterances. Such an approach has the advantage to be applicable to any unwritten (source) language.}, added-at = {2020-05-11T06:39:07.000+0200}, author = {Berard, Alexandre and Pietquin, Olivier and Servan, Christophe and Besacier, Laurent}, biburl = {https://www.bibsonomy.org/bibtex/2d4f5537049b45ccc1f691b46c57e5356/ramimanna}, description = {Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translation}, interhash = {d8d5b8482580efb068e4482dcb26b136}, intrahash = {d4f5537049b45ccc1f691b46c57e5356}, keywords = {mt speech}, note = {cite arxiv:1612.01744Comment: accepted to NIPS workshop on End-to-end Learning for Speech and Audio Processing}, timestamp = {2020-05-11T06:39:07.000+0200}, title = {Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translation}, url = {http://arxiv.org/abs/1612.01744}, year = 2016 }