{rfName}
To

Indexed in

License and use

Citations

Altmetrics

Analysis of institutional authors

Iranzo-Sánchez, JAuthorJorge, JAuthorSilvestre-Cerdà, JaAuthorCivera, JAuthorSanchis, AAuthorJuan, AAuthor
Share
Publications
>
Proceedings Paper

Towards simultaneous machine interpretation

Publicated to:19th Annual Conference Of The International Speech Communication Association (Interspeech 2018), Vols 1-6. 5 2277-2281 - 2021-01-01 5(), DOI: 10.21437/Interspeech.2021-201

Authors: Perez-Gonzalez-de-Martos, Alejandro; Iranzo-Sanchez, Javier; Gimenez Pastor, Adria; Jorge, Javier; Silvestre-Cerda, Joan-Albert; Civera, Jorge; Sanchis, Albert; Juan, Alfons

Affiliations

Univ Politecn Valencia, Valencian Res Inst Artificial Intelligence VRAIN, Machine Learning & Language Proc MLLP Res Grp - Author

Abstract

Automatic speech-to-speech translation (S2S) is one of the most challenging speech and language processing tasks, especially when considering its application to real-time settings. Recent advances on streaming Automatic Speech Recognition (ASR), simultaneous Machine Translation (MT) and incremental neural Text-To-Speech (TTS) make it possible to develop real-time cascade S2S systems with greatly improved accuracy. On the way to simultaneous machine interpretation, a state-of-the-art cascade streaming S2S system is described and empirically assessed in the simultaneous interpretation of European Parliament debates. We pay particular attention to the TTS component, particularly in terms of speech naturalness under a variety of response-time settings, as well as in terms of speaker similarity for its cross-lingual voice cloning capabilities.

Keywords
Automatic speechCharacter recognitionCloningComputer aided language translationCross-lingualCross-lingual voice cloningIncremental text-to-speechIts applicationsLanguage processingLstmMachine interpretationModelsNetworkOne-pass decoderReal time systemsSimultaneous machine interpretationSpeechSpeech communicationSpeech recognitionSpeech transmissionSpeech-to-speech translationText to speechTo-speech translation

Quality index

Impact and social visibility

From the perspective of influence or social adoption, and based on metrics associated with mentions and interactions provided by agencies specializing in calculating the so-called "Alternative or Social Metrics," we can highlight as of 2025-05-13:

  • The use of this contribution in bookmarks, code forks, additions to favorite lists for recurrent reading, as well as general views, indicates that someone is using the publication as a basis for their current work. This may be a notable indicator of future more formal and academic citations. This claim is supported by the result of the "Capture" indicator, which yields a total of: 15 (PlumX).
Leadership analysis of institutional authors

There is a significant leadership presence as some of the institution’s authors appear as the first or last signer, detailed as follows: First Author (Pérez-González-de-Martos, A) and Last Author (Juan Císcar, Alfonso).

the author responsible for correspondence tasks has been Pérez-González-de-Martos, A.