Zobrazeno 1 - 10
of 36
pro vyhledávání: '"Darko Pekar"'
Publikováno v:
Journal of Universal Computer Science, Vol 26, Iss 4, Pp 434-453 (2020)
The paper presents a novel architecture and method for training neural networks to produce synthesized speech in a particular voice and speaking style, based on a small quantity of target speaker/style training data. The method is based on neural net
Externí odkaz:
https://doaj.org/article/193b57b71be74119a2454a904ade13ec
Publikováno v:
2022 30th European Signal Processing Conference (EUSIPCO).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d231311254112b7158326a586a6ff8e2
https://doi.org/10.23919/eusipco55093.2022.9909548
https://doi.org/10.23919/eusipco55093.2022.9909548
Publikováno v:
Branislav Popović
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1c52267503feb64562ad1b3513ef830a
https://doi.org/10.23919/eusipco55093.2022.9909893
https://doi.org/10.23919/eusipco55093.2022.9909893
Publikováno v:
Telfor Journal, Vol 12, Iss 2, Pp 110-115 (2020)
In automatic speech recognition systems, the training data used for system development and the data actually obtained from the users of the system sometimes significantly differ in practice. However, other, more similar data may be available. Transfe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::53b70869915ea4ff85c4baeface1e033
https://doaj.org/article/c0c206fb4c314d368c0bf167d5db9957
https://doaj.org/article/c0c206fb4c314d368c0bf167d5db9957
Publikováno v:
Computational Intelligence and Neuroscience
Computational Intelligence and Neuroscience, Vol 2019 (2019)
Computational Intelligence and Neuroscience, Vol 2019 (2019)
Serbian is in a group of highly inflective and morphologically rich languages that use a lot of different word suffixes to express different grammatical, syntactic, or semantic features. This kind of behaviour usually produces a lot of recognition er
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3c5803b65a1a0abbc7e8a5b4ba49b451
https://doi.org/10.1155/2019/5072918
https://doi.org/10.1155/2019/5072918
Publikováno v:
Advances in Speech Recognition
Both ASR and TTS systems described in this chapter have been originally developed for the Serbian language. However, linguistic similarities among South Slavic languages have allowed the adaptation of this system to other South Slavic languages, with
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a5b8f967abf5e0d7bc27565df3f85526
http://www.intechopen.com/articles/show/title/speech-technologies-for-serbian-and-kindred-south-slavic-languages
http://www.intechopen.com/articles/show/title/speech-technologies-for-serbian-and-kindred-south-slavic-languages
Autor:
Dragisa Miskovic, Dragan Knezevic, Vlado Delic, Milan Sečujski, Nataša Vujnović Sedlar, Darko Pekar
Publikováno v:
Advances in Speech Recognition
The applications presented in this chapter clearly show the importance of development of speech technologies. Having in mind the extreme language dependence of these technologies, and the fact that, unlike most other technologies, they cannot simply
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::90d5e53bf86c4f63c525b92d013753fa
http://www.intechopen.com/articles/show/title/applications-of-speech-technologies-in-western-balkan-countries
http://www.intechopen.com/articles/show/title/applications-of-speech-technologies-in-western-balkan-countries
Publikováno v:
Speech and Computer ISBN: 9783030878016
SPECOM
SPECOM
The paper proposes a method for controlling the level of expressiveness of speech synthesis by linear interpolation between neural network embeddings corresponding to neutral and fully emotional speech. The deep neural network based speech synthesis
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::16c01e284b98b6f18f3835fb665a622e
https://doi.org/10.1007/978-3-030-87802-3_43
https://doi.org/10.1007/978-3-030-87802-3_43
Publikováno v:
JUCS-Journal of Universal Computer Science 26(4): 434-453
Journal of Universal Computer Science, Vol 26, Iss 4, Pp 434-453 (2020)
Journal of Universal Computer Science, Vol 26, Iss 4, Pp 434-453 (2020)
The paper presents a novel architecture and method for training neural networks to produce synthesized speech in a particular voice and speaking style, based on a small quantity of target speaker/style training data. The method is based on neural net
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d81776e0903f0e90e4365d24f2a9cd0b
https://zenodo.org/record/5508513
https://zenodo.org/record/5508513
Publikováno v:
2019 27th Telecommunications Forum (TELFOR).
In automatic speech recognition systems the training data used for system development and data expected to be obtained during the practical use of the system do not have to fit each other perfectly, but other similar data may be available. Transfer l
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8a88d482fa9eb0e57fba6e36f82c7c85
https://doi.org/10.1109/telfor48224.2019.8971335
https://doi.org/10.1109/telfor48224.2019.8971335