Zobrazeno 1 - 10
of 28
pro vyhledávání: '"Hari Krishna Vydana"'
Publikováno v:
IEEE Signal Processing Letters. 29:1729-1733
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5cdb6aef3b7d1392166f7cdceeac46ac
https://doi.org/10.1109/lsp.2022.3192199
https://doi.org/10.1109/lsp.2022.3192199
Publikováno v:
Circuits, Systems, and Signal Processing. 40:2376-2399
Fricatives are characterized by two prime acoustic properties, i.e., having high-frequency spectral concentration and possessing noisy nature. Spectral domain approaches for detecting fricatives employ a time–frequency representation to compute aco
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8b682a1bc6b749e4dedd2de1ca7f8354
https://doi.org/10.1007/s00034-020-01576-7
https://doi.org/10.1007/s00034-020-01576-7
Publikováno v:
Interspeech 2021.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b853478bffb41c72b15604eb7059e100
https://doi.org/10.21437/interspeech.2021-1756
https://doi.org/10.21437/interspeech.2021-1756
Publikováno v:
IWSLT
The paper describes BUT’s English to German offline speech translation (ST) systems developed for IWSLT2021. They are based on jointly trained Automatic Speech Recognition-Machine Translation models. Their performances is evaluated on MustC-Common
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::94131410f46ee96a9b7b3660cbb4926c
https://doi.org/10.18653/v1/2021.iwslt-1.7
https://doi.org/10.18653/v1/2021.iwslt-1.7
Publikováno v:
ICASSP
Conventional spoken language translation (SLT) systems are pipeline based systems, where we have an Automatic Speech Recognition (ASR) system to convert the modality of source from speech to text and a Machine Translation (MT) systems to translate so
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::73bb10cb8a719b0bfde5fb88213a4fde
http://arxiv.org/abs/2004.12111
http://arxiv.org/abs/2004.12111
Curriculum learning based approach for noise robust language identification using DNN with attention
Publikováno v:
Expert Systems with Applications. 110:290-297
Automatic language identification (LID) in practical environments is gaining a lot of scientific attention due to rapid developments in multilingual speech processing applications. When an LID is operated in noisy environments a degradation in the pe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::375c634d384b1bbcbd021bb66d17251a
https://doi.org/10.1016/j.eswa.2018.06.004
https://doi.org/10.1016/j.eswa.2018.06.004
Publikováno v:
ASRU
In this paper, phonetic features derived from the joint acoustic model (JAM) of a multilingual end to end automatic speech recognition system are proposed for Indian language identification (LID). These features utilize contextual information learned
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b11a327e6cbb4abfa19011a44d0dc0ad
https://doi.org/10.1109/asru46091.2019.9003784
https://doi.org/10.1109/asru46091.2019.9003784
Publikováno v:
INTERSPEECH
INTERSPEECH, 2019, Graz, Austria
INTERSPEECH, 2019, Graz, Austria
This work tackles the problem of learning a set of language specific acoustic units from unlabeled speech recordings given a set of labeled recordings from other languages. Our approach may be described by the following two steps procedure: first the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c11a1ada78296f9a153de8e7ad7162c6
https://doi.org/10.21437/interspeech.2019-2224
https://doi.org/10.21437/interspeech.2019-2224
Publikováno v:
IC3
Self-attention networks are being popularly employed in sequence classification and sequence summarization tasks. State-of-the-art models use sequential models to capture the high-level information, but these models are sensitive to length of utteran
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d715bb01de07d7f9944b8e6a6a2b6d42
https://doi.org/10.1109/ic3.2019.8844925
https://doi.org/10.1109/ic3.2019.8844925
Publikováno v:
The Journal of the Acoustical Society of America. 140:3896-3907
Two prime acoustic characteristics of fricatives are the concentration of spectral energy above 3 kHz and having noisy nature. Spectral domain approaches for detecting fricatives rely on capturing the information from spectral energy distribution. In
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::59e480f25c004c5303c945ee72bc07a3
https://doi.org/10.1121/1.4967517
https://doi.org/10.1121/1.4967517