Microphone Array Signal Processing

By Boaz Rafaely. 2008

666 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/e6f18dd6e177697ae9bf972fb9b087f2f3c6cbd7

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Signal Processing

Citations in the corpus

On the selection of the impulse responses for distant-speech recognition based on contaminated speech training (2014, background): “The literature in this field reports several possible approaches, which include the adoption of microphone arrays and related beamforming techniques, in order to perform a spatial filtering that emphasizes the speech input, while attenuating environmental noise and reverberation effects [4, 5].”
Complex Neural Spatial Filter: Enhancing Multi-Channel Target Speech Separation in Complex Domain (2021, methodology): “In our work, we follow the MVDR computation method in [32], and the coefficients w ∈ CU×F can be computed as follows:”
Multichannel Signal Processing With Deep Neural Networks for Automatic Speech Recognition (2017, background): “Note that the models presented in the previous subsection do not explicitly estimate the time delay of arrival of the target source arriving at different microphones, which is commonly done in beamforming [2].”
On Optimal Frequency-Domain Multichannel Linear Filtering for Noise Reduction (2010, methodology): “Indeed, it has been established that in addition to their very important task of localizing acoustic sources ([4] and references therein), microphone arrays allow for efficient source retrieval from mixtures of sounds and noise by taking advantage of the spatial dimension in addition to the classica”
A Consolidated Perspective on Multimicrophone Speech Enhancement and Source Separation (2017, neutral): “The relation between the parameters σ 2”
A Survey of Sound Source Localization with Deep Learning Methods (2021, neutral): “We do not detail those papers as well, since we focus on SSL in real-world reverberant environments.”
Speech acoustic modeling from raw multichannel waveforms (2015, background): “The right column shows the time domain ﬁlter weights and the left column shows the beampattern [10, Ch. 3], plotting the magnitude response of each ﬁlter as a function of direction of arrival relative to the microphone array.”
DeepMMSE: A Deep Learning Approach to MMSE-Based Noise Power Spectral Density Estimation (2020, background): “These algorithms can be broadly divided into two categories: single-channel [1]–[4] and multi-channel [5]–[8].”
Student-teacher network learning with enhanced features (2017, background): “In particular, when using multichannel speech enhancement techniques such as beamforming [5], significant improvements can be obtained compared to a single-channel ASR systems, and the state-of-the-art multichannel systems are approaching the performance of ASR systems in clean conditions [6, 7].”