Zobrazeno 1 - 10
of 23
pro vyhledávání: '"Korzekwa, Daniel"'
Recently normalizing flows have been gaining traction in text-to-speech (TTS) and voice conversion (VC) due to their state-of-the-art (SOTA) performance. Normalizing flows are unsupervised generative models. In this paper, we introduce supervision to
Externí odkaz:
http://arxiv.org/abs/2312.16552
Autor:
Bilinski, Piotr, Merritt, Thomas, Ezzerg, Abdelhamid, Pokora, Kamil, Cygert, Sebastian, Yanagisawa, Kayoko, Barra-Chicote, Roberto, Korzekwa, Daniel
Publikováno v:
Interspeech 2022, 2958-2962
Creating realistic and natural-sounding synthetic speech remains a big challenge for voice identities unseen during training. As there is growing interest in synthesizing voices of new speakers, here we investigate the ability of normalizing flows in
Externí odkaz:
http://arxiv.org/abs/2312.14569
Autor:
Zhang, Guangyan, Merritt, Thomas, Ribeiro, Manuel Sam, Tura-Vecino, Biel, Yanagisawa, Kayoko, Pokora, Kamil, Ezzerg, Abdelhamid, Cygert, Sebastian, Abbas, Ammar, Bilinski, Piotr, Barra-Chicote, Roberto, Korzekwa, Daniel, Lorenzo-Trueba, Jaime
Neural text-to-speech systems are often optimized on L1/L2 losses, which make strong assumptions about the distributions of the target data space. Aiming to improve those assumptions, Normalizing Flows and Diffusion Probabilistic Models were recently
Externí odkaz:
http://arxiv.org/abs/2307.16679
Autor:
Babianski, Mikolaj, Pokora, Kamil, Shah, Raahil, Sienkiewicz, Rafal, Korzekwa, Daniel, Klimkov, Viacheslav
Publikováno v:
2022 IEEE Spoken Language Technology Workshop (SLT), pp. 892-899
In expressive speech synthesis it is widely adopted to use latent prosody representations to deal with variability of the data during training. Same text may correspond to various acoustic realizations, which is known as a one-to-many mapping problem
Externí odkaz:
http://arxiv.org/abs/2301.11446
Autor:
Ezzerg, Abdelhamid, Merritt, Thomas, Yanagisawa, Kayoko, Bilinski, Piotr, Proszewska, Magdalena, Pokora, Kamil, Korzeniowski, Renard, Barra-Chicote, Roberto, Korzekwa, Daniel
Regional accents of the same language affect not only how words are pronounced (i.e., phonetic content), but also impact prosodic aspects of speech such as speaking rate and intonation. This paper investigates a novel flow-based approach to accent co
Externí odkaz:
http://arxiv.org/abs/2211.05850
Autor:
Korzekwa, Daniel
Despite significant advances in recent years, the existing Computer-Assisted Pronunciation Training (CAPT) methods detect pronunciation errors with a relatively low accuracy (precision of 60% at 40%-80% recall). This Ph.D. work proposes novel deep le
Externí odkaz:
http://arxiv.org/abs/2209.06265
The research community has long studied computer-assisted pronunciation training (CAPT) methods in non-native speech. Researchers focused on studying various model architectures, such as Bayesian networks and deep learning methods, as well as on the
Externí odkaz:
http://arxiv.org/abs/2207.00774
Autor:
Merritt, Thomas, Ezzerg, Abdelhamid, Biliński, Piotr, Proszewska, Magdalena, Pokora, Kamil, Barra-Chicote, Roberto, Korzekwa, Daniel
Non-parallel voice conversion (VC) is typically achieved using lossy representations of the source speech. However, ensuring only speaker identity information is dropped whilst all other information from the source speech is retained is a large chall
Externí odkaz:
http://arxiv.org/abs/2203.08009
Autor:
Ezzerg, Abdelhamid, Gabrys, Adam, Putrycz, Bartosz, Korzekwa, Daniel, Saez-Trigueros, Daniel, McHardy, David, Pokora, Kamil, Lachowicz, Jakub, Lorenzo-Trueba, Jaime, Klimkov, Viacheslav
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. However, not all speaking styles are easy to model: highly expr
Externí odkaz:
http://arxiv.org/abs/2108.06270
Autor:
Shah, Raahil, Pokora, Kamil, Ezzerg, Abdelhamid, Klimkov, Viacheslav, Huybrechts, Goeric, Putrycz, Bartosz, Korzekwa, Daniel, Merritt, Thomas
Whilst recent neural text-to-speech (TTS) approaches produce high-quality speech, they typically require a large amount of recordings from the target speaker. In previous work, a 3-step method was proposed to generate high-quality TTS while greatly r
Externí odkaz:
http://arxiv.org/abs/2106.12896