Zobrazeno 1 - 10
of 24
pro vyhledávání: '"Valentini Botinhão, Cássia"'
Machine learning approaches to modelling analog audio effects have seen intensive investigation in recent years, particularly in the context of non-linear time-invariant effects such as guitar amplifiers. For modulation effects such as phasers, howev
Externí odkaz:
http://arxiv.org/abs/2306.01332
We present a neural vocoder designed with low-powered Alternative and Augmentative Communication devices in mind. By combining elements of successful modern vocoders with established ideas from an older generation of technology, our system is able to
Externí odkaz:
http://arxiv.org/abs/2211.14130
Autor:
Webber, Jacob J, Valentini-Botinhao, Cassia, Williams, Evelyn, Henter, Gustav Eje, King, Simon
Publikováno v:
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Island, Greece, 2023, pp. 1-5
Most state-of-the-art Text-to-Speech systems use the mel-spectrogram as an intermediate representation, to decompose the task into acoustic modelling and waveform generation. A mel-spectrogram is extracted from the waveform by a simple, fast DSP oper
Externí odkaz:
http://arxiv.org/abs/2211.06989
Autor:
Valentini-Botinhao, Cassia, Ribeiro, Manuel Sam, Watts, Oliver, Richmond, Korin, Henter, Gustav Eje
Publikováno v:
Proceedings of INTERSPEECH 2022
Automatically predicting the outcome of subjective listening tests is a challenging task. Ratings may vary from person to person even if preferences are consistent across listeners. While previous work has focused on predicting listeners' ratings (me
Externí odkaz:
http://arxiv.org/abs/2209.11003
Autor:
Pine, Aidan, Cooper, Erica, Guzmán, David, Joanis, Eric, Kazantseva, Anna, Krekoski, Ross, Kuhn, Roland, Larkin, Samuel, Littell, Patrick, Lothian, Delaney, Martin, Akwiratékha’, Richmond, Korin, Tessier, Marc, Valentini-Botinhao, Cassia, Wells, Dan, Yamagishi, Junichi
Publikováno v:
In Computer Speech & Language March 2025 90
Autor:
Valentini-Botinhao, Cassia, Wester, Mirjam, Yamagishi, Junichi, Toman, Markus, Pucher, Michael, Schabus, Dietmar
We compare a series of time compression methods applied to normal and clear speech. First we evaluate a linear (uniform) method applied to these styles as well as to naturally-produced fast speech. We found, in line with the literature, that unproces
Externí odkaz:
http://arxiv.org/abs/1901.07239
Autor:
Valentini Botinhão, Cássia
Speech technology can facilitate human-machine interaction and create new communication interfaces. Text-To-Speech (TTS) systems provide speech output for dialogue, notification and reading applications as well as personalized voices for people that
Externí odkaz:
http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.615350
Autor:
Bollepalli, Bajibabu, Juvela, Lauri, Airaksinen, Manu, Valentini-Botinhao, Cassia, Alku, Paavo
Publikováno v:
In Speech Communication July 2019 110:64-75
Autor:
Pucher, Michael, Zillinger, Bettina, Toman, Markus, Schabus, Dietmar, Valentini-Botinhao, Cassia, Yamagishi, Junichi, Schmid, Erich, Woltron, Thomas
Publikováno v:
In Computer Speech & Language November 2017 46:179-195
Publikováno v:
In Computer Speech & Language January 2016 35:73-92