Zobrazeno 1 - 10
of 28
pro vyhledávání: '"Santos, João Felipe"'
Autor:
Badlani, Rohan, Arora, Akshit, Ghosh, Subhankar, Valle, Rafael, Shih, Kevin J., Santos, João Felipe, Ginsburg, Boris, Catanzaro, Bryan
We introduce VANI, a very lightweight multi-lingual accent controllable speech synthesis system. Our model builds upon disentanglement strategies proposed in RADMMM and supports explicit control of accent, language, speaker and fine-grained $F_0$ and
Externí odkaz:
http://arxiv.org/abs/2303.07578
Autor:
Badlani, Rohan, Valle, Rafael, Shih, Kevin J., Santos, João Felipe, Gururani, Siddharth, Catanzaro, Bryan
We work to create a multilingual speech synthesis system which can generate speech with the proper accent while retaining the characteristics of an individual voice. This is challenging to do because it is expensive to obtain bilingual training data
Externí odkaz:
http://arxiv.org/abs/2301.10335
Despite recent advances in generative modeling for text-to-speech synthesis, these models do not yet have the same fine-grained adjustability of pitch-conditioned deterministic models such as FastPitch and FastSpeech2. Pitch information is not only l
Externí odkaz:
http://arxiv.org/abs/2203.01786
Recent character and phoneme-based parametric TTS systems using deep learning have shown strong performance in natural speech generation. However, the choice between character or phoneme input can create serious limitations for practical deployment,
Externí odkaz:
http://arxiv.org/abs/1811.07240
Autor:
Santos, Joao Felipe, Falk, Tiago H.
In this paper, we propose a model to perform speech dereverberation by estimating its spectral magnitude from the reverberant counterpart. Our models are capable of extracting features that take into account both short and long-term dependencies in t
Externí odkaz:
http://arxiv.org/abs/1711.06309
Autor:
Trabelsi, Chiheb, Bilaniuk, Olexa, Zhang, Ying, Serdyuk, Dmitriy, Subramanian, Sandeep, Santos, João Felipe, Mehri, Soroush, Rostamzadeh, Negar, Bengio, Yoshua, Pal, Christopher J
At present, the vast majority of building blocks, techniques, and architectures for deep learning are based on real-valued operations and representations. However, recent work on recurrent neural networks and older fundamental theoretical analysis su
Externí odkaz:
http://arxiv.org/abs/1705.09792
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
We apply deep learning methods, specifically long short-term memory (LSTM) networks, to music transcription modelling and composition. We build and train LSTM networks using approximately 23,000 music transcriptions expressed with a high-level vocabu
Externí odkaz:
http://arxiv.org/abs/1604.08723
Autor:
Alvera-Azcárate, Aida, Van der Zande, Dimitry, Barth, Alexander, Cardoso dos Santos, João Felipe, Troupin, Charles, Beckers, Jean-Marie
Publikováno v:
In Remote Sensing of Environment February 2021 253
Autor:
Carvalho, Rozana Neves Guimarães de, Mendonça, Hugo Santos Lemos de, Silva, Jorge Luiz Lima da, Santos, João Felipe Magnani
Publikováno v:
Research, Society and Development; Vol. 11 No. 9; e19311931928
Research, Society and Development; Vol. 11 Núm. 9; e19311931928
Research, Society and Development; v. 11 n. 9; e19311931928
Research, Society and Development
Universidade Federal de Itajubá (UNIFEI)
instacron:UNIFEI
Research, Society and Development; Vol. 11 Núm. 9; e19311931928
Research, Society and Development; v. 11 n. 9; e19311931928
Research, Society and Development
Universidade Federal de Itajubá (UNIFEI)
instacron:UNIFEI
Objective: the main objective of the study is to describe the creation experiences and impressions about the use of an application on the prevention of human papillomavirus (HPV). The resource was applied during the theoretical-practical teaching of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______3056::14d5dd9f3b01233e674d90dd6bf414aa
https://rsdjournal.org/index.php/rsd/article/view/31928
https://rsdjournal.org/index.php/rsd/article/view/31928