For years speech translation has been faced as concatenation of speech recognition and machine translation. The powerful architectures of deep learning has made end-to-end speech translation feasible. The student will have to use the encoder-decoder architecture based on Transformer to build multilingual speech translation systems.Nowadays, there is a growing interest in the field of Speech Translation (speech-to-text). Traditionally, this task has been faced with the concatenation of Automatic Speech Recognition and Machine Translation modules. Nevertheless, in the last few years, many researchers have proposed the use of an end-to-end approach, in which the speech is not transcripted but directly translated into the target language. Furth...
We present a method for introducing a text encoder into pre-trained end-to-end speech translation sy...
Paper accepted to IWSLT 2021This paper describes the submission to the IWSLT 2021 offline speech tra...
End-to-end (E2E) speech-to-text translation (ST) often depends on pretraining its encoder and/or dec...
For years speech translation has been faced as concatenation of speech recognition and machine trans...
The introduction of speech translation corpora, which have speech signals aligned with the correspon...
Speech Recognition and Text-to-Text Translation systems have been improving significantly in recent ...
Direct speech-to-speech translation (S2ST) models suffer from data scarcity issues as there exists l...
This paper describes the submission to the IWSLT 2021 offline speech translation task by the UPC Mac...
International audienceWe investigate end-to-end speech-to-text translation on a corpus of audiobooks...
This paper describes the submission to the IWSLT 2021 offline speech translation task by the UPC Mac...
Speech Translation has been traditionally addressed with the concatenation of two tasks: Speech Reco...
Speech Recognition and Text-to-Text Translation systems have been improving significantly in recent ...
Speech Translation has been traditionally addressed with the concatenation of two tasks: Speech Reco...
This paper describes FBK’s submission to the end-to-end speech translation (ST) task at IWSLT 2019. ...
This paper describes FBK’s submission to the end-to-end speech translation (ST) task at IWSLT 2019. ...
We present a method for introducing a text encoder into pre-trained end-to-end speech translation sy...
Paper accepted to IWSLT 2021This paper describes the submission to the IWSLT 2021 offline speech tra...
End-to-end (E2E) speech-to-text translation (ST) often depends on pretraining its encoder and/or dec...
For years speech translation has been faced as concatenation of speech recognition and machine trans...
The introduction of speech translation corpora, which have speech signals aligned with the correspon...
Speech Recognition and Text-to-Text Translation systems have been improving significantly in recent ...
Direct speech-to-speech translation (S2ST) models suffer from data scarcity issues as there exists l...
This paper describes the submission to the IWSLT 2021 offline speech translation task by the UPC Mac...
International audienceWe investigate end-to-end speech-to-text translation on a corpus of audiobooks...
This paper describes the submission to the IWSLT 2021 offline speech translation task by the UPC Mac...
Speech Translation has been traditionally addressed with the concatenation of two tasks: Speech Reco...
Speech Recognition and Text-to-Text Translation systems have been improving significantly in recent ...
Speech Translation has been traditionally addressed with the concatenation of two tasks: Speech Reco...
This paper describes FBK’s submission to the end-to-end speech translation (ST) task at IWSLT 2019. ...
This paper describes FBK’s submission to the end-to-end speech translation (ST) task at IWSLT 2019. ...
We present a method for introducing a text encoder into pre-trained end-to-end speech translation sy...
Paper accepted to IWSLT 2021This paper describes the submission to the IWSLT 2021 offline speech tra...
End-to-end (E2E) speech-to-text translation (ST) often depends on pretraining its encoder and/or dec...