Mateusz Łajszczak
Mateusz Łajszczak
Geverifieerd e-mailadres voor amazon.com
Geciteerd door
Geciteerd door
In other news: A bi-style text-to-speech model for synthesizing newscaster voice with limited data
N Prateek, M Łajszczak, R Barra-Chicote, T Drugman, J Lorenzo-Trueba, ...
arXiv preprint arXiv:1904.02790, 2019
Interpretable deep learning model for the detection and reconstruction of dysarthric speech
D Korzekwa, R Barra-Chicote, B Kostek, T Drugman, M Lajszczak
arXiv preprint arXiv:1907.04743, 2019
Varying speaking styles with neural textto-speech
T Wood, T Merritt
Amazon Science, 2018
Simple and effective multi-sentence TTS with expressive and coherent prosody
P Makarov, A Abbas, M Łajszczak, A Joly, S Karlapati, A Moinet, ...
arXiv preprint arXiv:2206.14643, 2022
CopyCat2: A Single Model for Multi-Speaker TTS and Many-to-Many Fine-Grained Prosody Transfer
S Karlapati, P Karanasou, M Lajszczak, A Abbas, A Moinet, P Makarov, ...
arXiv preprint arXiv:2206.13443, 2022
Distribution augmentation for low-resource expressive text-to-speech
M Lajszczak, A Prasad, A Van Korlaar, B Bollepalli, A Bonafonte, A Joly, ...
ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022
Discrete acoustic space for an efficient sampling in neural text-to-speech
M Strelec, J Rohnke, A Bonafonte, M Łajszczak, T Wood
arXiv preprint arXiv:2110.12539, 2021
Het systeem kan de bewerking nu niet uitvoeren. Probeer het later opnieuw.
Artikelen 1–7