Zobrazeno 1 - 10
of 92
pro vyhledávání: '"Gábor Csapó"'
Publikováno v:
the Proceedings of Interspeech 2023
Thanks to the latest deep learning algorithms, silent speech interfaces (SSI) are now able to synthesize intelligible speech from articulatory movement data under certain conditions. However, the resulting models are rather speaker-specific, making a
Externí odkaz:
http://arxiv.org/abs/2305.19130
Autor:
Dániel Gábor Csapó
Publikováno v:
Romanian Journal of European Affairs, Vol 20, Iss 2, Pp 100-119 (2020)
Although China attempts to present itself as a leader of the fight against climate change – and, in some aspects, is taking initiative in this respect – through the Belt and Road Initiative the country has lent support to many ‘dirty’ proje
Externí odkaz:
https://doaj.org/article/f774144ebfc04799a99bc25463389125
Publikováno v:
Sensors, Vol 23, Iss 4, p 1971 (2023)
Speech is the most spontaneous and natural means of communication. Speech is also becoming the preferred modality for interacting with mobile or fixed electronic devices. However, speech interfaces have drawbacks, including a lack of user privacy; no
Externí odkaz:
https://doaj.org/article/50b7027657d642d59434b45b154d721e
Publikováno v:
Sensors, Vol 22, Iss 22, p 8601 (2022)
Within speech processing, articulatory-to-acoustic mapping (AAM) methods can apply ultrasound tongue imaging (UTI) as an input. (Micro)convex transducers are mostly used, which provide a wedge-shape visual image. However, this process is optimized fo
Externí odkaz:
https://doaj.org/article/80c85c4f4ec340d3a7ddbec6dd86472c
Publikováno v:
Multimedia Tools and Applications. 82:15635-15649
This paper presents an investigation of speaker adaptation using a continuous vocoder for parametric text-to-speech (TTS) synthesis. In purposes that demand low computational complexity, conventional vocoder-based statistical parametric speech synthe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::12aa625da854bc37f4e0d3bd6a05f306
https://doi.org/10.1007/s11042-022-14005-5
https://doi.org/10.1007/s11042-022-14005-5
Publikováno v:
Beszedtudomany - Speech Science; 2024, Vol. 4 Issue 1, p158-184, 27p
Publikováno v:
Applied Sciences, Vol 11, Iss 16, p 7489 (2021)
Voice conversion (VC) transforms the speaking style of a source speaker to the speaking style of a target speaker by keeping linguistic information unchanged. Traditional VC techniques rely on parallel recordings of multiple speakers uttering the sam
Externí odkaz:
https://doaj.org/article/0931fd748ab94e599540bb8bf560e1a8
Autor:
Kang You, Bo Liu, Kele Xu, Yunsheng Xiong, Qisheng Xu, Ming Feng, Tamás Gábor Csapó, Boqing Zhu
Publikováno v:
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::14f9fdcba1811d7f7dd56ce8ab1d7bcb
https://doi.org/10.1109/icassp49357.2023.10095156
https://doi.org/10.1109/icassp49357.2023.10095156
Publikováno v:
Infocommunications journal. 14:55-62
Speech synthesis has the aim of generating humanlike speech from text. Nowadays, with end-to-end systems, highly natural synthesized speech can be achieved if a large enough dataset is available from the target speaker. However, often it would be nec
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::917d4c178bfe95dae9a7f41658171e65
https://doi.org/10.36244/icj.2022.3.7
https://doi.org/10.36244/icj.2022.3.7
Publikováno v:
Acta Polytechnica Hungarica. 19:93-112
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5c8479ceb1ad7d89e8b0b1201ca6effc
https://doi.org/10.12700/aph.19.1.2022.1.7
https://doi.org/10.12700/aph.19.1.2022.1.7