Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Mattia Antonino Di Gangi"'
Publikováno v:
IWSLT
Scopus-Elsevier
Scopus-Elsevier
This paper describes the offline and simultaneous speech translation systems developed at AppTek for IWSLT 2021. Our offline ST submission includes the direct end-to-end system and the so-called posterior tight integrated model, which is akin to the
Publikováno v:
INTERSPEECH
Direct speech-to-text translation (ST) models are usually trained on corpora segmented at sentence level, but at inference time they are commonly fed with audio split by a voice activity detector (VAD). Since VAD segmentation is not syntax-informed,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::73e9500bb65a3a7db12651eced707009
http://arxiv.org/abs/2008.02270
http://arxiv.org/abs/2008.02270
Autor:
Marco Turchi, Roldano Cattoni, Matteo Negri, Mattia Antonino Di Gangi, Luisa Bentivogli, Beatrice Savoldi
Publikováno v:
ACL
Translating from languages without productive grammatical gender like English into gender-marked languages is a well-known difficulty for machines. This difficulty is also due to the fact that the training data on which models are built typically ref
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8b8833ce5b570711e2b4f3f9de9abfcf
http://arxiv.org/abs/2006.05754
http://arxiv.org/abs/2006.05754
Publikováno v:
CLiC-it
Scopus-Elsevier
Università degli di Trento-IRIS
Scopus-Elsevier
Università degli di Trento-IRIS
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 know
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0635bc22cde6a5a8655ec3b8eec303d3
https://doi.org/10.4000/books.aaccademia.8585
https://doi.org/10.4000/books.aaccademia.8585
Publikováno v:
Computational Intelligence Methods for Bioinformatics and Biostatistics ISBN: 9783030345846
CIBB
CIBB
Nucleosomes are the fundamental repeating unit of chromatin. A nucleosome is an 8 histone proteins complex, in which approximately 147–150 pairs of DNA bases bind. Several biological studies have clearly stated that the regulation of cell type-spec
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1f2c618255e6f5add0fd469ad8819804
http://hdl.handle.net/10447/393825
http://hdl.handle.net/10447/393825
Publikováno v:
IWSLT
This paper describes FBK's participation in the IWSLT 2020 offline speech translation (ST) task. The task evaluates systems' ability to translate English TED talks audio into German texts. The test talks are provided in two versions: one contains the
Publikováno v:
ICASSP
Despite recent technology advancements, the effectiveness of neural approaches to end-to-end speech-to-text translation is still limited by the paucity of publicly available training corpora. We tackle this limitation with a method to improve data ex
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b87e11dd11949ac65b0b39fe29b0bb7d
http://arxiv.org/abs/1910.10663
http://arxiv.org/abs/1910.10663
Publikováno v:
ASRU
Nowadays, training end-to-end neural models for spoken language translation (SLT) still has to confront with extreme data scarcity conditions. The existing SLT parallel corpora are indeed orders of magnitude smaller than those available for the close
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::70380c4f79f3553085a4d858ab988749
http://arxiv.org/abs/1910.03320
http://arxiv.org/abs/1910.03320
Publikováno v:
INTERSPEECH
Publikováno v:
INTERSPEECH
Machine translation systems are conventionally trained on textual resources that do not model phenomena that occur in spoken language. While the evaluation of neural machine translation systems on textual inputs is actively researched in the literatu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ae540f6847895a31462aef5db9c3e390
http://arxiv.org/abs/1904.10997
http://arxiv.org/abs/1904.10997