Discriminative learning of receptive fields from responses to non-Gaussian stimulus ensembles.

Autor: Arne F Meyer, Jan-Philipp Diepenbrock, Max F K Happel, Frank W Ohl, Jörn Anemüller

Publikováno v: PLoS ONE, Vol 9, Iss 4, p e93062 (2014)

Analysis of sensory neurons' processing characteristics requires simultaneous measurement of presented stimuli and concurrent spike responses. The functional transformation from high-dimensional stimulus space to the binary space of spike and non-spi

Externí odkaz: https://doaj.org/article/2c9f20921f7248d9919c711173f45726

Machine listening in spatial acoustic scenes with deep networks in different microphone geometries

Autor: Jörn Anemüller

Publikováno v: Proceedings of the Northern Lights Deep Learning Workshop; Vol. 1 (2020): Proceedings of the Northern Lights Deep Learning Workshop 2020; 6

Multi-channel acoustic source localization evaluates direction-dependentinter-microphone differences in order to estimate the position of an acousticsource embedded in an interfering sound field. We here investigate a deep neuralnetwork (DNN) approac

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c1921a38e2b0548b1f2306b97e0b517a
https://septentrio.uit.no/index.php/nldl/article/view/5151

Spectro-Temporal Gabor Filterbank Features for Acoustic Event Detection

Autor: Stefan Goetze, Jörn Anemüller, Jens Schroder

Publikováno v: IEEE/ACM Transactions on Audio, Speech, and Language Processing. 23:2198-2208

Algorithms for the automatic detection and recognition of acoustic events are increasingly gaining relevance for the reliable and robust functioning of consumer, assistive and monitoring systems. The extraction of appropriate task relevant acoustic f

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f8b48fe1a6b18e94f7a474983eec93de
https://doi.org/10.1109/taslp.2015.2467964

Multi-channel signal enhancement with speech and noise covariance estimates computed by a probabilistic localization model

Autor: Hendrik Kayser, Jörn Anemüller

Publikováno v: ICASSP

Classic approaches to multi-channel signal enhancement rely on model assumptions regarding speech source relative transfer functions and noise covariance matrix, or on estimates thereof obtained in, e.g., speech pauses. To alleviate these constraints

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::5401025b3f54cb4b2ebb4ba4f590b583
https://doi.org/10.1109/icassp.2017.7952137

Acoustic Source Localization by Combination of Supervised Direction-of-Arrival Estimation with Disjoint Component Analysis

Autor: Jörn Anemüller, Hendrik Kayser

Publikováno v: Latent Variable Analysis and Signal Separation ISBN: 9783319535463
LVA/ICA

Analysis and processing in reverberant, multi-source acoustic environments encompasses a multitude of techniques that estimate from sensor signals a spatially resolved “image” of acoustic space, a high-level representation of physical sources tha

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::a33ca6f415348b2c52fd95f11adb7a78
https://doi.org/10.1007/978-3-319-53547-0_10