no code implementations • 20 Jun 2023 • Jakub Swiatkowski, Duo Wang, Mikolaj Babianski, Giuseppe Coccia, Patrick Lumban Tobing, Ravichander Vipperla, Viacheslav Klimkov, Vincent Pollet
Speech generation for machine dubbing adds complexity to conventional Text-To-Speech solutions as the generated output is required to match the expressiveness, emotion and speaking rate of the source content.
no code implementations • 26 Jan 2023 • Mikolaj Babianski, Kamil Pokora, Raahil Shah, Rafal Sienkiewicz, Daniel Korzekwa, Viacheslav Klimkov
In expressive speech synthesis it is widely adopted to use latent prosody representations to deal with variability of the data during training.
no code implementations • 13 Aug 2021 • Abdelhamid Ezzerg, Adam Gabrys, Bartosz Putrycz, Daniel Korzekwa, Daniel Saez-Trigueros, David McHardy, Kamil Pokora, Jakub Lachowicz, Jaime Lorenzo-Trueba, Viacheslav Klimkov
Artificial speech synthesis has made a great leap in terms of naturalness as recent Text-to-Speech (TTS) systems are capable of producing speech with similar quality to human recordings.
no code implementations • 24 Jun 2021 • Raahil Shah, Kamil Pokora, Abdelhamid Ezzerg, Viacheslav Klimkov, Goeric Huybrechts, Bartosz Putrycz, Daniel Korzekwa, Thomas Merritt
In this paper, we present a method for building highly expressive TTS voices with as little as 15 minutes of speech data from the target speaker.
no code implementations • 16 Jun 2021 • Adam Gabryś, Yunlong Jiao, Viacheslav Klimkov, Daniel Korzekwa, Roberto Barra-Chicote
In the waveform reconstruction task, the proposed model closes the naturalness and signal quality gap from the original PW to recordings by $10\%$, and from other state-of-the-art neural vocoding systems by more than $60\%$.
no code implementations • 1 Feb 2021 • Yunlong Jiao, Adam Gabrys, Georgi Tinchev, Bartosz Putrycz, Daniel Korzekwa, Viacheslav Klimkov
We present a universal neural vocoder based on Parallel WaveNet, with an additional conditioning network called Audio Encoder.
no code implementations • 4 Jul 2019 • Viacheslav Klimkov, Srikanth Ronanki, Jonas Rohnke, Thomas Drugman
However, when trained on a single-speaker dataset, the conventional prosody transfer systems are not robust enough to speaker variability, especially in the case of a reference signal coming from an unseen speaker.
no code implementations • 4 Mar 2019 • Thomas Drugman, Goeric Huybrechts, Viacheslav Klimkov, Alexis Moinet
In this paper, we consider voicing detection as a classification problem and F0 contour estimation as a regression problem.