Zobrazeno 1 - 10
of 78
pro vyhledávání: '"Josef Psutka"'
Publikováno v:
Text, Speech, and Dialogue ISBN: 9783031162695
Czech is a very specific language due to its large differences between the formal and the colloquial form of speech. While the formal (written) form is used mainly in official documents, literature, and public speeches, the colloquial (spoken) form i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::276f1ba67284136bc3d8f4abc4bbcc19
http://arxiv.org/abs/2206.07666
http://arxiv.org/abs/2206.07666
In this paper, we present our progress in pretraining Czech monolingual audio transformers from a large dataset containing more than 80 thousand hours of unlabeled speech, and subsequently fine-tuning the model on automatic speech recognition tasks u
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ba68731a462d5f2f3a0a0b00f91c13e6
http://arxiv.org/abs/2206.07627
http://arxiv.org/abs/2206.07627
The paper describes a novel approach to Spoken Term Detection (STD) in large spoken archives using deep LSTM networks. The work is based on the previous approach of using Siamese neural networks for STD and naturally extends it to directly localize a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1c2dead702f41ae336dfb2a43bca9bef
Publikováno v:
Multimedia Tools and Applications. 79:1203-1220
Tento článek představuje originální systém pro titulkování živého televizního vysílání využívající stínové přemlouvání a automatické rozpoznávání řeči. Na rozdíl od několika komerčně dostupných řešení pro živé t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::596b3eb1167e54be3492594a3ed8bfbc
https://doi.org/10.1007/s11042-019-08235-3
https://doi.org/10.1007/s11042-019-08235-3
Autor:
Josef Psutka
Publikováno v:
Pattern Recognition. 91:25-33
The significant properties of the maximum likelihood (ML) estimate are consistency, normality, and efficiency. While it has been proven that these properties are valid when the sample size approaches infinity, the behavior of an ML estimator when wor
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::454fbd1172655fa479fcb17b59b34f53
https://doi.org/10.1016/j.patcog.2019.01.046
https://doi.org/10.1016/j.patcog.2019.01.046
Publikováno v:
Statistical Language and Speech Processing ISBN: 9783030895785
SLSP
SLSP
V tomto článku diskutujeme některé zajímavé rysy trénování speciálního akustického modelu pouze pro jednoho řečníka s konstantním akustickým pozadím (akustický kanál). V současné době metoda LF-MMI dosahuje nejlepších výsled
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::974b774fa0d19651c6b8ab83f9b9b574
http://hdl.handle.net/11025/47266
http://hdl.handle.net/11025/47266
Publikováno v:
Text, Speech, and Dialogue ISBN: 9783030835262
TDS
TDS
Czech and Slovak languages are very similar, not only in writing but also in phonetic form. This work aims to find a suitable combination of these two languages concerning better recognition results. We would like to show such a contribution on the M
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6b79f40f456d7e9cfafdc1bccc7320e8
https://doi.org/10.1007/978-3-030-83527-9_45
https://doi.org/10.1007/978-3-030-83527-9_45
Publikováno v:
Speech and Computer ISBN: 9783030878016
SPECOM
SPECOM
The Malach Project [6] verified the possibility of using automatic speech recognition (ASR) methods to search for information in large multilingual archives of Holocaust testimonies. After the end of the MALACH project, in which we participated, we c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f9140189f5281b300eff79a3e5acaa09
http://hdl.handle.net/11025/47254
http://hdl.handle.net/11025/47254
Autor:
Josef Psutka, Petr Stanislav
Publikováno v:
Speech and Computer ISBN: 9783030602758
SPECOM
SPECOM
Pacienti, kteří podstoupili totální laryngektomii a používají k produkci hlasu elektrolarynx, trpí špatnou srozumitelností. V mnoha případech to může vést k obavám z mluvení s cizími lidmi, a to i po telefonu. Systémy automatickéh
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b88ea1e21eeb135cd912d9edae409755
https://doi.org/10.1007/978-3-030-60276-5_54
https://doi.org/10.1007/978-3-030-60276-5_54
Publikováno v:
Text, Speech, and Dialogue ISBN: 9783030583224
TDS
TDS
In this paper, we discuss some of the properties of training acoustic models using a lattice-free version of the maximum mutual information criterion (LF-MMI). Currently, the LF-MMI method achieves state-of-the-art results on many speech recognition
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3e0954787af912082d6201b9eec10577
http://hdl.handle.net/11025/42718
http://hdl.handle.net/11025/42718