Robust Localization in Reverberant Rooms

By Joseph H. DiBiase, H. Silverman, M. Brandstein. Microphone Arrays, 2001

702 citations recorded by the source corpus.

Subfields: Electrical and Electronic Engineering, Signal Processing

View Paper: https://www.semanticscholar.org/paper/4fa20ba4142796bf4b7841519f4808f82f43beee

How researchers see this paper

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

In Electrical and Electronic Engineering

In Signal Processing

Citations in the corpus

The third ‘CHiME’ speech separation and recognition challenge: Dataset, task and baselines (2015, neutral): “Second, the spatial position of the speaker in the real recordings is tracked using the steered response power phase transform (SRP-PHAT) algorithm [11] (see Section 4.”
Neural Network Adaptive Beamforming for Robust Multichannel Speech Recognition (2016, background): “However, it is difficult to accurately estimate the time delay of arrival in reverberant environments [11] and DS beamforming does not take into account the effect of spatially correlated noise.”
Kullback-Leibler Divergence (2011, methodology): “We now consider a special case of the simple and widely used delay-and-sum beamformer-based sound localization technique [20], [ 16 ], [22], [2], [9], [21].”
Multi-Channel Deep Clustering: Discriminative Spectral and Spatial Embeddings for Speaker-Independent Speech Separation (2018, methodology): “Motivated by [18] and the GCC-PHAT algorithm [24], we derive the following spatial feature for model training: where N is the frame length, θ t,f,p,q is the observed phase difference, τ is the hypothesized time delay in samples, and 2 τ is the hypothesized phase difference.”
Sound Event Localization and Detection of Overlapping Sources Using Convolutional Recurrent Neural Networks (2018, background): “On the other hand, subspace methods require a good estimate of the number of active sources that may be hard to obtain, and they have been found sensitive to reverberant and low signal-to-noise (SNR) scenarios [48].”
Generalization of Multi-Channel Linear Prediction Methods for Blind MIMO Impulse Response Shortening (2012, positive): “This property is required since many source localization algorithms are explicitly or implicitly based on TDOAs at microphone positions [1].”
Recognition of overlapping speech using digital MEMS microphone arrays (2013, methodology): “Speaker localisation is carried out by using a superdirective variant of the original steered response power (SRP-PHAT) method from [15, 16].”
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.”
A French Corpus for Distant-Microphone Speech Processing in Real Homes (2016, positive): “As a baseline, we used our own implementation of the state-of-the-art SRP-PHAT algorithm [30].”
Automatic analysis of multimodal group actions in meetings (2005, methodology): ““Speech activity” was computed as the Steered Response Power coming from each location using the SRP-PHAT measure [52], [53], which is a continuous, bounded value that indicates the activity of a particular location.”
An analysis of environment, microphone and data simulation mismatches in robust speech recognition (2017, positive): “Therefore, simulation was based on tracking the spatial position of the speaker in the real recordings using the SRP-PHAT algorithm (DiBiase et al., 2001) and generating the time-varying pure delay filter corresponding to the direct path between the speaker’s mouth and the microphones instead.”