Zobrazeno 1 - 10
of 28
pro vyhledávání: '"Sinisa Suzic"'
Autor:
Nikola Simić, Siniša Suzić, Nemanja Milošević, Vuk Stanojev, Tijana Nosek, Branislav Popović, Dragana Bajović
Publikováno v:
Applied Sciences, Vol 14, Iss 4, p 1325 (2024)
Human–machine interaction covers a range of applications in which machines should understand humans’ commands and predict their behavior. Humans commonly change their mood over time, which affects the way we interact, particularly by changing spe
Externí odkaz:
https://doaj.org/article/4f1c4e144f5f44cbb171188adbd8d3fd
Publikováno v:
2022 30th European Signal Processing Conference (EUSIPCO).
Publikováno v:
2022 30th European Signal Processing Conference (EUSIPCO).
Publikováno v:
2021 29th Telecommunications Forum (TELFOR).
Autor:
Tijana Durkic, Aleksandra Lojanicic, Sinisa Suzic, Branislav Popovic, Milan Secujski, Tijana Nosek
Publikováno v:
2021 29th Telecommunications Forum (TELFOR).
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:
Elektronika ir Elektrotechnika, Vol 24, Iss 4, Pp 64-67 (2018)
The overall distortion of semilogarithmic A law quantizer is influenced by its support region, as well as parameter A. Current solutions require numerical determination of optimal support region and larger processing time, i.e. simple closed-form sol
Publikováno v:
2019 27th Telecommunications Forum (TELFOR).
The paper presents systems based on convolutional neural networks designed to classify genuine and artificially generated speech signals, which were evaluated on database for logical access designed for 3rd Automatic Speaker Verification Spoofing and
Publikováno v:
Telfor Journal (2017) 9(1):32-37
Telfor Journal, Vol 9, Iss 1, Pp 32-37 (2017)
Telfor Journal, Vol 9, Iss 1, Pp 32-37 (2017)
In this paper the research related to the development of a deep neural network based speech synthesizer for the Serbian language, trained on recorded utterances of a single female voice talent, is described. Two separate networks are used for predict