Zobrazeno 1 - 10
of 12
pro vyhledávání: '"Carbajal, Guillaume"'
Emotions are subjective constructs. Recent end-to-end speech emotion recognition systems are typically agnostic to the subjective nature of emotions, despite their state-of-the-art performance. In this work, we introduce an end-to-end Bayesian neural
Externí odkaz:
http://arxiv.org/abs/2110.03299
Publikováno v:
2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)
Recently, the standard variational autoencoder has been successfully used to learn a probabilistic prior over speech signals, which is then used to perform speech enhancement. Variational autoencoders have then been conditioned on a label describing
Externí odkaz:
http://arxiv.org/abs/2105.08970
Publikováno v:
ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Recently, a generative variational autoencoder (VAE) has been proposed for speech enhancement to model speech statistics. However, this approach only uses clean speech in the training phase, making the estimation particularly sensitive to noise prese
Externí odkaz:
http://arxiv.org/abs/2102.08706
Publikováno v:
ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Recently, variational autoencoders have been successfully used to learn a probabilistic prior over speech signals, which is then used to perform speech enhancement. However, variational autoencoders are trained on clean speech only, which results in
Externí odkaz:
http://arxiv.org/abs/2102.06454
Publikováno v:
IEEE/ACM Transactions on Audio, Speech and Language Processing 2020
We consider the problem of simultaneous reduction of acoustic echo, reverberation and noise. In real scenarios, these distortion sources may occur simultaneously and reducing them implies combining the corresponding distortion-specific filters. As th
Externí odkaz:
http://arxiv.org/abs/1911.08934
Autor:
Carbajal, Guillaume
Publikováno v:
Informatique [cs]. Université de Lorraine, 2020. Français. ⟨NNT : 2020LORR0017⟩
This PhD falls within the development of hands-free telecommunication systems, more specifically smart speakers in domestic environments. The user interacts with another speaker at a far-end point and can be typically a few meters away from this kind
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::48848d646270f74514406b0a35ce7262
https://hal.univ-lorraine.fr/tel-02877545
https://hal.univ-lorraine.fr/tel-02877545
Autor:
Carbajal, Guillaume
Publikováno v:
Informatique [cs]. Université de Lorraine, 2020. Français. ⟨NNT : 2020LORR0017⟩
This PhD falls within the development of hands-free telecommunication systems, more specifically smart speakers in domestic environments. The user interacts with another speaker at a far-end point and can be typically a few meters away from this kind
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od_______212::48848d646270f74514406b0a35ce7262
https://hal.univ-lorraine.fr/tel-02877545
https://hal.univ-lorraine.fr/tel-02877545
Publikováno v:
[Research Report] RR-9303, INRIA Nancy; Invoxia SAS. 2019
[Research Report] RR-9303, INRIA Nancy, équipe Multispeech; Invoxia SAS. 2019
[Research Report] RR-9303, INRIA Nancy, équipe Multispeech; Invoxia SAS. 2019
This technical report is the supporting document of our proposed approach basedon a neural network for joint multichannel reduction of echo, reverberation and noise [1]. First, werecall the model of the proposed approach. Secondly, we express the vec
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::e29612e16968d356704ffcac2f52e484
https://hal.inria.fr/hal-02372431
https://hal.inria.fr/hal-02372431
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
France, N° de brevet: 1760200. 2017
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::405653591ac2790fb02887e239a66259
https://hal.inria.fr/hal-01638050
https://hal.inria.fr/hal-01638050