Optimal Bayesian Speech Enhancement by Parametric Joint Detection and Estimation

Autor: Van-Khanh Mai, Dominique Pastor, Abdeldjalil Aissa-El-Bey

Publikováno v: IEEE Access, Vol 8, Pp 15695-15710 (2020)

In this paper, we propose a general framework to estimate short-time spectral amplitudes (STSA) of speech signals in noise by joint speech detection and estimation to remove or reduce background noise, without increasing signal distortion. The approa

Externí odkaz: https://doaj.org/article/f86575a3c1e9487a92843c05d0a80988

Acoustic Echo Cancellation Embedded in Smart Transcoding Algorithm between 3GPP AMR-NB Modes

Autor: Emmanuel Rossignol Thepie Fapi, Dominique Pastor, Christophe Beaugeant, Hervé Taddei

Publikováno v: Journal of Electrical and Computer Engineering, Vol 2010 (2010)

Acoustic Echo Cancellation (AEC) is a necessary feature for mobile devices when the acoustic coupling between the microphone and the loudspeaker affects the communication quality and intelligibility. When implemented inside the network, decoding is r

Externí odkaz: https://doaj.org/article/6d831da6e32b4ad88551364467292aac

On joint parameterizations of linear and nonlinear functionals in neural networks

Autor: Abdourrahmane Mahamane Atto, Sylvie Galichet, Dominique Pastor, Nicolas Méger

Publikováno v: Neural networks : the official journal of the International Neural Network Society. 160

The paper proposes a new class of nonlinear operators and a dual learning paradigm where optimization jointly concerns both linear convolutional weights and the parameters of these nonlinear operators. The nonlinear class proposed to perform a rich f

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9adf651c2cb55595c0adcf17fcfc2a81
https://pubmed.ncbi.nlm.nih.gov/36592526

Truncated Sequential Non-Parametric Hypothesis Testing Based on Random Distortion Testing

Autor: Vinod Sharma, Prashant Khanduri, Pramod K. Varshney, Dominique Pastor

Publikováno v: IEEE Transactions on Signal Processing
IEEE Transactions on Signal Processing, Institute of Electrical and Electronics Engineers, 2019, 67 (15), pp.4027-4042. ⟨10.1109/TSP.2019.2923140⟩

International audience; In this work, we propose a new algorithm for sequential non-parametric hypothesis testing based on Random Distortion Testing (RDT). The data based approach is non-parametric in the sense that the underlying signal distribution

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a6860aa7a9ee40e5b72ce00555ed6d3b
https://doi.org/10.1109/tsp.2019.2923140

Asymptotic Random Distortion Testing and Application to Change-in-Mean Detection

Autor: Guillaume Ansel, Nora Cuppens, Dominique Pastor, Frédéric Cuppens

Publikováno v: ISIVC'2020: 10th International Symposium on Signal, Image, Video and Communications
ISIVC'2020: 10th International Symposium on Signal, Image, Video and Communications, Apr 2021, Saint-Étienne (virtual), France. ⟨10.1109/ISIVC49222.2021.9487550⟩
ISIVC

International audience; We introduce an extension of the Random Distortion Testing (RDT) framework which allows its use when the noise variance is estimated. This asymptotic extension, named AsympRDT, shows that we asymptotically retain the level of

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9c5b6f5a3112d6f6c1447f4683e0ab01
https://hal-imt-atlantique.archives-ouvertes.fr/hal-03238994