Proceedings ArticleDOI
A Multichannel Kalman-Based Wiener Filter Approach for Speaker Interference Reduction in Meetings
Patrick Meyer,Samy Elshamy,Tim Fingscheidt +2 more
- pp 451-455
Reads0
Chats0
TLDR
This work extends an existing approach by integrating methods from acoustic echo cancellation to improve the estimation of the interferer (noise) components of the filter, which leads to an improved signal-to-interferer ratio by up to 2.1 dB absolute at constant speech component quality.Abstract:
Recording a meeting and obtaining clean speech signals of each speaker is a challenging task. Even with a multichannel recording, in which all speakers are equipped with a close-talk microphone, speech of an active speaker still couples not only into his dedicated microphone, but also into all other microphone channels at a certain level. This is denoted as crosstalk and requires a multichannel speaker interference reduction to enhance the microphone channels for further processing. To solve this issue, we use a Wiener filter which is based on all individual microphone channels. We extend an existing approach by integrating methods from acoustic echo cancellation to improve the estimation of the interferer (noise) components of the filter, which leads to an improved signal-to-interferer ratio by up to 2.1 dB absolute at constant speech component quality.read more
Citations
More filters
Journal ArticleDOI
Distributed Combined Acoustic Echo Cancellation and Noise Reduction in Wireless Acoustic Sensor and Actuator Networks
TL;DR: The paper presents distributed algorithms for combined acoustic echo cancellation (AEC) and noise reduction (NR) in a wireless acoustic sensor and actuator network (WASAN) where each node may have multiple microphones and multiple loudspeakers, and where the desired signal is a speech signal.
Posted Content
From a Fourier-Domain Perspective on Adversarial Examples to a Wiener Filter Defense for Semantic Segmentation
Nikhil Kapoor,Andreas Bär,Serin Varghese,Jan David Schneider,Fabian Hüger,Peter Schlicht,Tim Fingscheidt +6 more
TL;DR: An adversarial defense method based on the well-known Wiener filters that captures and suppresses adversarial frequencies in a data-driven manner is proposed that not only generalizes across unseen attacks but also beats five existing state-of-the-art methods across two models in a variety of attack settings.
Proceedings ArticleDOI
From a Fourier-Domain Perspective on Adversarial Examples to a Wiener Filter Defense for Semantic Segmentation
Nikhil Kapoor,Andreas Bär,Serin Varghese,Jan David Schneider,Fabian Hüger,Peter Schlicht,Tim Fingscheidt +6 more
TL;DR: In this article, the authors study the adversarial problem from a frequency domain perspective and propose an adversarial defense method based on the well-known Wiener filters that captures and suppresses adversarial frequencies in a data-driven manner.
Journal ArticleDOI
Multichannel speaker interference reduction using frequency domain adaptive filtering
TL;DR: An adaptive filter method is integrated, which was originally proposed for acoustic echo cancellation (AEC), in order to obtain a well-performing interferer (noise) component estimation and results in an improved speech-to-interferer ratio by up to 2.7 dB at constant or even better speech component quality.
Proceedings ArticleDOI
Machine learning based noise suppression in narrow-band speech communication systems
TL;DR: In this article , a machine learning based noise suppression approach that uses a neuro-fuzzy logic-based neural network for noise estimation and reduction is proposed, which is shown to give significant improvements in noise suppression compared to a non-adaptive approach.
References
More filters
Posted Content
Rethinking Atrous Convolution for Semantic Image Segmentation
TL;DR: The proposed `DeepLabv3' system significantly improves over the previous DeepLab versions without DenseCRF post-processing and attains comparable performance with other state-of-art models on the PASCAL VOC 2012 semantic image segmentation benchmark.
Proceedings ArticleDOI
Deep clustering: Discriminative embeddings for segmentation and separation
TL;DR: In this paper, a deep network is trained to assign contrastive embedding vectors to each time-frequency region of the spectrogram in order to implicitly predict the segmentation labels of the target spectrogram from the input mixtures.
Proceedings ArticleDOI
The ICSI Meeting Corpus
Adam Janin,Don Baron,Jane A. Edwards,Daniel P. W. Ellis,David Gelbart,Nelson Morgan,Barbara Peskin,Thilo Pfau,Elizabeth Shriberg,Andreas Stolcke,Chuck Wooters +10 more
TL;DR: A corpus of data from natural meetings that occurred at the International Computer Science Institute in Berkeley, California over the last three years is collected, which supports work in automatic speech recognition, noise robustness, dialog modeling, prosody, rich transcription, information retrieval, and more.
Journal ArticleDOI
Multitalker Speech Separation With Utterance-Level Permutation Invariant Training of Deep Recurrent Neural Networks
TL;DR: In this article, the utterance-level permutation invariant training (uPIT) technique was proposed for speaker independent multitalker speech separation, where RNNs, trained with uPIT, can separate multitalker mixed speech without any prior knowledge of signal duration, number of speakers, speaker identity, or gender.
Posted Content
Deep clustering: Discriminative embeddings for segmentation and separation
TL;DR: Preliminary experiments on single-channel mixtures from multiple speakers show that a speaker-independent model trained on two-speaker mixtures can improve signal quality for mixtures of held-out speakers by an average of 6dB, and the same model does surprisingly well with three-speakers mixtures.
Related Papers (5)
Adaptive microphone array free of the desired speaker cancellation combined with postfilter
Slobodan Jovicic,Zoran Saric +1 more