Localisation et rehaussement de sources de parole au format Ambisonique : analyse de scènes sonores pour faciliter la commande vocale

Autor: Perotin, Lauréline

Cette thèse s'inscrit dans le contexte de l'essor des assistants vocaux mains libres. Dans un environnement domestique, l'appareil est généralement posé à un endroit fixe, tandis que le locuteur s'adresse à lui depuis diverses positions, sans n

Externí odkaz: http://www.theses.fr/2019LORR0124/document

Localization and enhancement of speech from the Ambisonics format

Autor: Perotin, Lauréline

Publikováno v: Traitement du signal et de l'image [eess.SP]. Université de Lorraine, 2019. Français. ⟨NNT : 2019LORR0124⟩

This work was conducted in the fast-growing context of hands-free voice command. In domestic environments, smart devices are usually laid in a fixed position, while the human speaker gives orders from anywhere, not necessarily next to the device, or

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::49d46fceafefef228dc01d95143c1055
https://hal.univ-lorraine.fr/tel-02393258/document

Regression versus classification for neural network based audio source localization

Autor: Alexandre Défossez, Alexandre Guerin, Emmanuel Vincent, Romain Serizel, Laureline Perotin

Publikováno v: WASPAA
WASPAA 2019-IEEE Workshop on Applications of Signal Processing to Audio and Acoustics
WASPAA 2019-IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, IEEE, Oct 2019, New Paltz, United States

International audience; We compare the performance of regression and classification neural networks for single-source direction-of-arrival estimation. Since the output space is continuous and structured, regression seems more appropriate. However, cl

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e53e7a2f36dfe70e0f0c28479789e1f0
https://hal.inria.fr/hal-02125985v2

Multichannel Speech Separation with Recurrent Neural Networks from High-Order Ambisonics Recordings

Autor: Emmanuel Vincent, Alexandre Guerin, Romain Serizel, Laureline Perotin

Publikováno v: ICASSP
43rd IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2018)
43rd IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2018), Apr 2018, Calgary, Canada

International audience; We present a source separation system for high-order ambisonics (HOA) contents. We derive a multichannel spatial filter from a mask estimated by a long short-term memory (LSTM) recurrent neural network. We combine one channel

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a1981cb166dd3b63bab9b647618fb309
https://doi.org/10.1109/icassp.2018.8461370