End-To-End Label Uncertainty Modeling for Speech-based Arousal Recognition Using Bayesian Neural Networks

Autor: Navin Raj Prabhu, Guillaume Carbajal, Nale Lehmann-Willenbrock, Timo Gerkmann

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: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4d8eef43fc5dbaac5c4636d4811d3c7f
http://arxiv.org/abs/2110.03299

Guided Variational Autoencoder for Speech Enhancement With a Supervised Classifier

Autor: Guillaume Carbajal, Timo Gerkmann, Julius Richter

Publikováno v: 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: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6341a1b1c1794d4e8d2367bd05b59b46

Variational Autoencoder for Speech Enhancement with a Noise-Aware Encoder

Autor: Huajian Fang, Stefan Wermter, Guillaume Carbajal, Timo Gerkmann

Publikováno v: 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: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::90a4b5c9eed0c10ed8094a13173e32ff

Joint NN-Supported Multichannel Reduction of Acoustic Echo, Reverberation and Noise

Autor: Emmanuel Vincent, Guillaume Carbajal, Romain Serizel, Eric Humbert

Publikováno v: IEEE/ACM Transactions on Audio, Speech and Language Processing
IEEE/ACM Transactions on Audio, Speech and Language Processing, 2020, ⟨10.1109/TASLP.2020.3008974⟩
IEEE/ACM Transactions on Audio, Speech and Language Processing, Institute of Electrical and Electronics Engineers, 2020, ⟨10.1109/TASLP.2020.3008974⟩

International audience; 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

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c230428f900da2722467b4b208283e75
https://hal.inria.fr/hal-02372579v3/document