Zobrazeno 1 - 10
of 31
pro vyhledávání: '"Gilles Degottex"'
Autor:
Mark J. F. Gales, Gilles Degottex
Publikováno v:
SLT
Generative networks can create an artificial spectrum based on its conditional distribution estimate instead of predicting only the mean value, as the Least Square (LS) solution does. This is promising since the LS predictor is known to oversmooth fe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a352d3e908efc5ed959cc1270076b6b0
https://doi.org/10.1109/slt.2018.8639609
https://doi.org/10.1109/slt.2018.8639609
Publikováno v:
SLT
Speech synthesis technology has a wide range of applications such as voice assistants. In recent years waveform-level synthesis systems have achieved state-of-the-art performance, as they overcome the limitations of vocoder-based synthesis systems. A
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cfb7eeb11047c83d143a2358ac39393f
https://doi.org/10.1109/slt.2018.8639588
https://doi.org/10.1109/slt.2018.8639588
Publikováno v:
SLT
This work investigates techniques that select training data from small, found corpuses in order to improve the naturalness of synthesized text-to-speech voices. The approach outlined in this paper examines different metrics to detect and reject segme
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::591ca8eb1058e058f8f336404654e803
https://doi.org/10.1109/slt.2018.8639642
https://doi.org/10.1109/slt.2018.8639642
Publikováno v:
INTERSPEECH
© 2018 International Speech Communication Association. All rights reserved. Speaker adaptation is a key aspect of building a range of speech processing systems, for example personalised speech synthesis. For deep-learning based approaches, the model
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0f0be0c62eeff0e7547cbed329d890d5
Publikováno v:
IEEE/ACM Transactions on Audio, Speech, and Language Processing
Most of the degradation in current Statistical Parametric Speech Synthesis (SPSS) results from the form of the vocoder. One of the main causes of degradation is the reconstruction of the noise. In this article, a new signal model is proposed that lea
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a0f7caa7d87e65f69ce672897c80aa6f
Autor:
Gilles Degottex
Publikováno v:
IEEE Signal Processing Letters. 22:978-982
In most applications of sinusoidal models for speech signal, an amplitude spectral envelope is necessary. This envelope is not only assumed to fit the vocal tract filter response as accurately as possible, but it should also exhibit slow varying shap
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2a3e186e79b9824dc7b6e685cf17214b
https://doi.org/10.1109/lsp.2014.2380412
https://doi.org/10.1109/lsp.2014.2380412
Publikováno v:
ASRU
Enabling speech synthesis systems to rapidly adapt to sound like a particular speaker is an essential attribute for building personalised systems. For deep-learning based approaches, this is difficult as these networks use a highly distributed repres
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3438e9e3de971fa9b244e555943cd2c7
https://doi.org/10.1109/asru.2017.8269006
https://doi.org/10.1109/asru.2017.8269006
Autor:
Yannis Stylianou, Gilles Degottex
Publikováno v:
IEEE Transactions on Acoustics Speech and Language Processing
Voice models often use frequency limits to split the speech spectrum into two or more voiced/unvoiced frequency bands. However, from the voice production, the amplitude spectrum of the voiced source decreases smoothly without any abrupt frequency lim
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::994644fed51499468cac82768a4cd9d5
Publikováno v:
SSW
The quality of the vocoder plays a crucial role in the performance of parametric speech synthesis systems. In order to improve the vocoder quality, it is necessary to reconstruct as much of the perceived components of the speech signal as possible. I
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::892195b059a5600ffa0326cda34df436
https://doi.org/10.21437/ssw.2016-35
https://doi.org/10.21437/ssw.2016-35
Publikováno v:
IEEE/ACM Transactions on Audio, Speech and Language Processing
IEEE/ACM Transactions on Audio, Speech and Language Processing, Institute of Electrical and Electronics Engineers, 2016, 24 (7), pp.1242-1254
IEEE/ACM Transactions on Audio, Speech and Language Processing, 2016, 24 (7), pp.1242-1254
IEEE/ACM Transactions on Audio, Speech and Language Processing, Institute of Electrical and Electronics Engineers, 2016, 24 (7), pp.1242-1254
IEEE/ACM Transactions on Audio, Speech and Language Processing, 2016, 24 (7), pp.1242-1254
International audience; Singing voice synthesis benefits from very high-quality estimation of the resonances and anti-resonances of the vocal tract filter (VTF), i.e., an amplitude spectral envelope. In the state of the art, a single frame of DFT tra
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f91b1f2267fca4111986da3f7a995264
https://hal.archives-ouvertes.fr/hal-01448760
https://hal.archives-ouvertes.fr/hal-01448760