Zobrazeno 1 - 10
of 11
pro vyhledávání: '"Thomas Haubner"'
Publikováno v:
EURASIP Journal on Audio, Speech, and Music Processing, Vol 2020, Iss 1, Pp 1-15 (2020)
Abstract Ego-noise, i.e., the noise a robot causes by its own motions, significantly corrupts the microphone signal and severely impairs the robot’s capability to interact seamlessly with its environment. Therefore, suitable ego-noise suppression t
Externí odkaz:
https://doaj.org/article/2a80b66ef2994ec4bc8271d5c9df1f28
In many daily-life scenarios, acoustic sources recorded in an enclosure can only be observed with other interfering sources. Hence, convolutive Blind Source Separation (BSS) is a central problem in audio signal processing. Methods based on Independen
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b02e1ed4833053e1d79307258aaefeff
http://arxiv.org/abs/2207.13934
http://arxiv.org/abs/2207.13934
We describe a joint acoustic echo cancellation (AEC) and blind source extraction (BSE) approach for multi-microphone acoustic frontends. The proposed algorithm blindly estimates AEC and beamforming filters by maximizing the statistical independence o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8c84431e9230a8ac1ce28033dc5e4642
Publikováno v:
IEEE Transactions on Signal Processing. 68:3545-3558
Signal separation and extraction are important tasks for devices recording audio signals in real environments which, aside from the desired sources, often contain several interfering sources such as background noise or concurrent speakers. Blind Sour
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::414c24e31c9f1ff01c660c9174738789
https://doi.org/10.1109/tsp.2020.3000199
https://doi.org/10.1109/tsp.2020.3000199
We introduce a synergistic approach to double-talk robust acoustic echo cancellation combining adaptive Kalman filtering with a deep neural network-based postfilter. The proposed algorithm overcomes the well-known limitations of Kalman filter-based a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::aaa90d83c08a9d0aa6f5bda5dd579878
http://arxiv.org/abs/2012.08867
http://arxiv.org/abs/2012.08867
Publikováno v:
MLSP
In this paper we present a novel algorithm for improved block-online supervised acoustic system identification in adverse noise scenarios by exploiting prior knowledge about the space of Room Impulse Responses (RIRs). The method is based on the assum
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c56a0cfa9211d510c8a0ee4104e2a82f
https://doi.org/10.1109/mlsp49062.2020.9231543
https://doi.org/10.1109/mlsp49062.2020.9231543
Publikováno v:
ICASSP
We present a noise-robust adaptation control strategy for block-online supervised acoustic system identification by exploiting a noise dictionary. The proposed algorithm takes advantage of the pronounced spectral structure which characterizes many ty
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::241016c669cf23d84233670e6fd71721
http://arxiv.org/abs/2007.01579
http://arxiv.org/abs/2007.01579
Publikováno v:
ICASSP
We present a Maximum A Posteriori (MAP) derivation of the Independent Vector Analysis (IVA) algorithm for blind source separation incorporating an additional spatial prior over the demixing matrices. In this way, the outer permutation ambiguity of IV
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1254cd4d48247591490e6bb4f2bea35b
https://doi.org/10.1109/icassp40776.2020.9052905
https://doi.org/10.1109/icassp40776.2020.9052905
Publikováno v:
ICASSP
In this contribution, we introduce a novel approach to noise-robust acoustic echo cancellation employing a complex-valued Deep Neural Network (DNN) for postfiltering. In a first step, early linear echo components are removed using a double-talk robus
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d300b99f0d9e573e5745e507b34cf8b1
Publikováno v:
EUSIPCO
In this paper, we address the task of active acoustic source tracking as part of robotic path planning. It denotes the planning of sequences of robotic movements to enhance tracking results of acoustic sources, e.g., talking humans, by fusing observa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::efeeaeca6178f7a1e42e083ffc2f9ae9
https://doi.org/10.23919/eusipco.2019.8902566
https://doi.org/10.23919/eusipco.2019.8902566