Attention-based distributed speech enhancement for unconstrained microphone arrays with varying number of nodes

  title={Attention-based distributed speech enhancement for unconstrained microphone arrays with varying number of nodes},
  author={Nicolas Furnon and Romain Serizel and Slim Essid and Irina Illina},
  journal={2021 29th European Signal Processing Conference (EUSIPCO)},
Speech enhancement promises higher efficiency in ad-hoc microphone arrays than in constrained microphone arrays thanks to the wide spatial coverage of the devices in the acoustic scene. However, speech enhancement in ad-hoc microphone arrays still raises many challenges. In particular, the algorithms should be able to handle a variable number of microphones, as some devices in the array might appear or disappear. In this paper, we propose a solution that can efficiently process the spatial… 
1 Citations

Figures from this paper

Time-domain Ad-hoc Array Speech Enhancement Using a Triple-path Network

This work proposes a novel triple-path network for ad-hoc array processing in the time domain that is a multiple-input multiple-output architecture that can simultaneously enhance signals at all microphones.



DNN-Based Mask Estimation for Distributed Speech Enhancement in Spatially Unconstrained Microphone Arrays

This paper proposes to extend a previously introduced distributed DNN-based time-frequency mask estimation scheme that can efficiently use spatial information in form of so-called compressed signals which are pre-filtered target estimations.

DNN-based Distributed Multichannel Mask Estimation for Speech Enhancement in Microphone Arrays

This work proposes to extend the distributed adaptive node-specific signal estimation approach to a neural network framework and shows that this additional signal can be leveraged to predict the masks and leads to better speech enhancement performance than when the mask estimation relies only on the local signals.

End-to-end Microphone Permutation and Number Invariant Multi-channel Speech Separation

This paper proposes transform-average-concatenate (TAC), a simple design paradigm for channel permutation and number invariant multi-channel speech separation based on the filter-and-sum network, and shows how TAC significantly improves the separation performance across various numbers of microphones in noisy reverberant separation tasks with ad-hoc arrays.

Rate-Constrained Noise Reduction in Wireless Acoustic Sensor Networks

A rate-constrained multi-microphone noise reduction algorithm, which jointly finds the best rate allocation and estimation weights for the microphones across all frequencies, and the optimal linear estimators are found to be the quantized Wiener filters.

A Low-Cost Robust Distributed Linearly Constrained Beamformer for Wireless Acoustic Sensor Networks With Arbitrary Topology

Two variants of the proposed beamformer are presented and evaluated in the context of multimicrophone speech enhancement in a wireless acoustic sensor network, and are compared with other state-of-the-art distributed beamformers in terms of communication costs and robustness to RATF estimation errors and TAD errors.

Neural network based spectral mask estimation for acoustic beamforming

A neural network based approach to acoustic beamforming is presented, used to estimate spectral masks from which the Cross-Power Spectral Density matrices of speech and noise are estimated, which are used to compute the beamformer coefficients.

Distributed MVDR Beamforming for (Wireless) Microphone Networks Using Message Passing

A distributed algorithm for MVDR beamforming which is based on message passing which does not require any constraint on the network topology, is fully scalable and can exploit sparse network geometries, thereby making it suitable for distributed signal processing in large scale networks.

Rate-Constrained Collaborative Noise Reduction for Wireless Hearing Aids

  • O. RoyM. Vetterli
  • Computer Science, Physics
    IEEE Transactions on Signal Processing
  • 2009
This work investigates the noise reduction capability of hearing instruments that may exchange data by means of a rate-constrained wireless link and thus benefit from the signals recorded at both ears of the user under two different coding strategies.

Performance measurement in blind audio source separation

This paper considers four different sets of allowed distortions in blind audio source separation algorithms, from time-invariant gains to time-varying filters, and derives a global performance measure using an energy ratio, plus a separate performance measure for each error term.

Diffusion-based distributed MVDR beamformer

  • Matthew O'ConnorW. Kleijn
  • Computer Science
    2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2014
A distributed beamforming method based on the diffusion adaptation paradigm that does not impose conditions on the topology or the structure of the network nor does it require knowledge of the noise co-variance matrix, making it suitable for a practical, dynamic environment.