Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Poncelet, Jakob"'
Continuous speech can be converted into a discrete sequence by deriving discrete units from the hidden features of self-supervised learned (SSL) speech models. Although SSL models are becoming larger and trained on more data, they are often sensitive
Externí odkaz:
http://arxiv.org/abs/2409.02565
Autor:
Poncelet, Jakob, Van hamme, Hugo
Self-supervised pre-trained speech models have strongly improved speech recognition, yet they are still sensitive to domain shifts and accented or atypical speech. Many of these models rely on quantisation or clustering to learn discrete acoustic uni
Externí odkaz:
http://arxiv.org/abs/2309.13994
Autor:
Poncelet, Jakob, Van hamme, Hugo
TV subtitles are a rich source of transcriptions of many types of speech, ranging from read speech in news reports to conversational and spontaneous speech in talk shows and soaps. However, subtitles are not verbatim (i.e. exact) transcriptions of sp
Externí odkaz:
http://arxiv.org/abs/2210.07771
Autor:
Poncelet, Jakob, Van hamme, Hugo
Recent research in speech processing exhibits a growing interest in unsupervised and self-supervised representation learning from unlabelled data to alleviate the need for large amounts of annotated data. We investigate several popular pre-training m
Externí odkaz:
http://arxiv.org/abs/2109.14357
Autor:
Poncelet, Jakob, Van hamme, Hugo
Voice controlled applications can be a great aid to society, especially for physically challenged people. However this requires robustness to all kinds of variations in speech. A spoken language understanding system that learns from interaction with
Externí odkaz:
http://arxiv.org/abs/2002.07450
Publikováno v:
In Computer Speech & Language March 2021 66
Autor:
Poncelet, Jakob, Van hamme, Hugo
Publikováno v:
2022 IEEE Spoken Language Technology Workshop (SLT).
TV subtitles are a rich source of transcriptions of many types of speech, ranging from read speech in news reports to conversational and spontaneous speech in talk shows and soaps. However, subtitles are not verbatim (i.e. exact) transcriptions of sp
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::987c5521d537e97ca1b9a4e42f96e2f7
https://doi.org/10.1109/slt54892.2023.10022420
https://doi.org/10.1109/slt54892.2023.10022420