Results 11 to 20 of about 7,097,775 (327)
Direct Speech-to-Speech Translation with a Sequence-to-Sequence Model [PDF]
Interspeech 2019, 2019 Accepted to Interspeech ...
Ye Jia +6 more
openaire +4 more sources
Direct Speech to Speech Translation: A Review
CoRRSpeech to speech translation (S2ST) is a transformative technology that bridges global communication gaps, enabling real time multilingual interactions in diplomacy, tourism, and international trade. Our review examines the evolution of S2ST, comparing traditional cascade models which rely on automatic speech recognition (ASR), machine translation (MT),
Mohammad Sarim +4 more
openaire +3 more sources
Direct Speech Translation for Automatic Subtitling [PDF]
Transactions of the Association for Computational Linguistics, 2023 Abstract Automatic subtitling is the task of automatically translating the speech of audiovisual content into short pieces of timed text, i.e., subtitles and their corresponding timestamps. The generated subtitles need to conform to space and time requirements, while being synchronized with the speech and segmented in a way that ...
Sara Papi +5 more
openaire +7 more sources
On the Locality of Attention in Direct Speech Translation [PDF]
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop, 2022 ACL-SRW 2022.
Alastruey Lasheras, Belén +3 more
openaire +4 more sources
On Knowledge Distillation for Direct Speech Translation [PDF]
CLICIT, 2020 Direct speech translation (ST) has shown to be a complex task requiring knowledge transfer from its sub-tasks: automatic speech recognition (ASR) and machine translation (MT). For MT, one of the most promising techniques to transfer knowledge is knowledge distillation. In this paper, we compare the different solutions to distill knowledge in a sequence-
Gaido M. +3 more
openaire +7 more sources
Direct speech reconstruction from sensorimotor brain activity with optimized deep learning models. [PDF]
J Neural Eng, 2023 Objective. Development of brain–computer interface (BCI) technology is key for enabling communication in individuals who have lost the faculty of speech due to severe motor paralysis.
Berezutskaya J +5 more
europepmc +2 more sources
Students’ Ability at Changing Direct into Indirect Speech and Indirect into Direct Speech [PDF]
Budapest International Research and Critics Institute (BIRCI-Journal) : Humanities and Social Sciences, 2019 Reported speech is one of difficult topics in learning English grammar, especially in changing the form from direct into indirect or reverse. Descriptive quantitative was used to find out the students’ ability in changing direct into indirect speech and reverse. There were five sentences that were changed by the students for two kinds of test.
Muhammad Dalimunte, Maryati Salmiah
openaire +2 more sources
Neurolinguistics Research Advancing Development of a Direct-Speech Brain-Computer Interface. [PDF]
iScience, 2018 A direct-speech brain-computer interface (DS-BCI) acquires neural signals corresponding to imagined speech, then processes and decodes these signals to produce a linguistic output in the form of phonemes, words, or sentences.
Cooney C, Folli R, Coyle D.
europepmc +2 more sources
Recent Advances in Direct Speech-to-text Translation [PDF]
International Joint Conference on Artificial Intelligence, 2023 Recently, speech-to-text translation has attracted more and more attention and many studies have emerged rapidly. In this paper, we present a comprehensive survey on direct speech translation aiming to summarize the current state-of-the-art techniques ...
Chen Xu +7 more
semanticscholar +1 more source
UnitY: Two-pass Direct Speech-to-speech Translation with Discrete Units [PDF]
Annual Meeting of the Association for Computational Linguistics, 2022 Direct speech-to-speech translation (S2ST), in which all components can be optimized jointly, is advantageous over cascaded approaches to achieve fast inference with a simplified pipeline.
H. Inaguma +9 more
semanticscholar +1 more source