Výsledky vyhledávání - "Anemüller Jörn"

Report

Single-Channel Speech Enhancement with Deep Complex U-Networks and Probabilistic Latent Space Models

Autor: Nustede, Eike J., Anemüller, Jörn

Publikováno v: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Island, Greece, 2023, pp. 1-5

In this paper, we propose to extend the deep, complex U-Network architecture for speech enhancement by incorporating a probabilistic (i.e., variational) latent space model. The proposed model is evaluated against several ablated versions of itself in

Externí odkaz: http://arxiv.org/abs/2309.01535

Zobrazit plný text záznamu

Akademický článek

Evaluation and comparison of different machine learning approaches to auditory spectro-temporal receptive field estimation

Autor: Ohl Frank W, Diepenbrock Jan P, Meyer Arne F, Anemüller Jörn

Publikováno v: BMC Neuroscience, Vol 12, Iss Suppl 1, p P4 (2011)

Externí odkaz: https://doaj.org/article/b108d55200674dc787570c14d8dd19e1

Zobrazit plný text záznamu

Akademický článek

Estimation of spectro-temporal receptive fields based on linear support vector machine classification

Autor: Ohl Frank W, Happel Max FK, Meyer Arne F, Anemüller Jörn

Publikováno v: BMC Neuroscience, Vol 10, Iss Suppl 1, p P147 (2009)

Externí odkaz: https://doaj.org/article/7747f06090db4d67a339d39682a27542

Zobrazit plný text záznamu

Report

Towards speech enhancement using a variational U-Net architecture

Autor: Nustede, Eike J., Anemüller, Jörn

We investigate the viability of a variational U-Net architecture for denoising of single-channel audio data. Deep network speech enhancement systems commonly aim to estimate filter masks, or opt to work on the waveform signal, potentially neglecting

Externí odkaz: http://arxiv.org/abs/2012.03594

Zobrazit plný text záznamu