Zobrazeno 1 - 10
of 63
pro vyhledávání: '"Daniel Tihelka"'
Autor:
Marie Kunešová, Jindřich Matoušek, Jan Lehečka, Jan Švec, Josef Michálek, Daniel Tihelka, Martin Bulín, Zdeněk Hanzlíček, Markéta Řezáčková
Publikováno v:
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Autor:
Jindřich Matoušek, Daniel Tihelka
Publikováno v:
Text, Speech, and Dialogue ISBN: 9783031162695
In this paper, we investigate two research questions related to the phonetic representation of input text in Czech neural speech synthesis: 1) whether we can afford to reduce the phonetic alphabet, and 2) whether we can remove pauses from phonetic tr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::63b0e63c22a30411ea81a42f2ae5d00f
http://hdl.handle.net/11025/50927
http://hdl.handle.net/11025/50927
Autor:
Jindřich Matoušek, Daniel Tihelka
Publikováno v:
Artificial Neural Networks in Pattern Recognition ISBN: 9783031206498
In this paper, we propose to frame glottal closure instant (GCI) de- tection from raw speech as a sequence-to-sequence prediction problem and to explore the potential of recurrent neural networks (RNNs) to handle this prob- lem. We compare the RNN ar
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e074dff07c95e73769aa1c06d23a20cd
http://hdl.handle.net/11025/51298
http://hdl.handle.net/11025/51298
Publikováno v:
Interspeech 2021.
Despite the increasing popularity of end-to-end text-to-speech (TTS) systems, the correct grapheme-to-phoneme (G2P) module is still a crucial part of those relying on a phonetic input. In this paper, we, therefore, introduce a T5G2P model, a Text-to-
Publikováno v:
Language Resources and Evaluation. 53:449-464
Článek představuje motivaci k vytváření specializovaných řečových korpusů o řízení letového provozu, podrobně popisuje proces přípravy korpusů pro automatické rozpoznávání řeči a převod textu na řeč (řečovou syntézu), D
Publikováno v:
Text, Speech, and Dialogue ISBN: 9783030835262
TDS
TDS
In recent years, the concept of end-to-end text-to-speech synthesis has begun to attract the attention of researchers. The motivation is simple – replacing the individual modules that TTS traditionally built on with a powerful deep neural network s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f3599481eff4af16d33f655568f910f0
http://hdl.handle.net/11025/47247
http://hdl.handle.net/11025/47247
Autor:
Daniel Tihelka, Markéta Jůzová
Publikováno v:
Text, Speech, and Dialogue ISBN: 9783030583224
TDS
TDS
Phrase boundary detection is an important part of text-to-speech systems since it ensures more natural speech synthesis outputs. However, the problem of phrasing is ambiguous, especially per speaker and per style. This is the reason why this paper fo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::686d93905e7b0de73640bbb65fa2edb0
https://doi.org/10.1007/978-3-030-58323-1_37
https://doi.org/10.1007/978-3-030-58323-1_37
Publikováno v:
Speech and Computer ISBN: 9783030602758
SPECOM
SPECOM
While unit selection speech synthesis is not at the centre of research nowadays, it shows its strengths in deployments where fast fixes and tuning possibilities are required. The key part of this method is target and concatenation costs, usually cons
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7108bdfd03f1d551d8f932e1b66bfeed
https://doi.org/10.1007/978-3-030-60276-5_56
https://doi.org/10.1007/978-3-030-60276-5_56
Článek se zabývá syntézou expresivní řeči v dialogu. Pro popis expresivity jsou použity dialogové akty - diskrétní expresivní kategorie. Cílem této práce je popsat postup vývoje expresivní syntézy řeči pro dialogový systém v om
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::746997e310c91b1090997097f84f3a38
http://hdl.handle.net/11025/42621
http://hdl.handle.net/11025/42621
Publikováno v:
Speech and Computer ISBN: 9783030602758
SPECOM
SPECOM
Modern web browsers are becoming operating systems of their own kind, allowing unified access to the underlying hardware. The sound device can thus be used by web-based communication systems, such a Google meet, Zoom and others. This attracts the ide
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f342da3e622af34760a1074a7dd7a88d
https://doi.org/10.1007/978-3-030-60276-5_57
https://doi.org/10.1007/978-3-030-60276-5_57