A novel approach to localization of environmental noise sources: Sub-windowing for time domain beamforming

The case that multiple speakers are simultaneously active is usually regarded as adverse condition in the context of multi-source direction-of-arrival (DOA) estimation. Moreover, in adjacent sources scenarios, classifying DOA estimates by directions may merge adjacent sources and misclassify reverberation as sources, i.e., there is a mismatch between sources and reverberation. In order to address the open challenges mentioned above, this work introduces a pipeline for selecting reliable time-frequency (TF) bins and estimating multi-source DOAs using a single acoustic vector sensor (AVS). In the proposed pipeline, we show a viewpoint that the multiple simultaneously active sources condition can be exploited to select TF bins solely dominated by sources. The consistency of the distribution of intensity vectors (IVs) in multi-source scenarios is derived mathematically to support the proposed viewpoint. We address the mismatch between sources and reverberations in adjacent sources scenarios by focusing only on the direction with the highest intensity vector density (IVD), regardless of how many sources dominate the given TF window. Simulation and experimental results show that the proposed method can accurately and robustly estimate the multi-source DOAs in various scenarios.

A Time-Frequency Bins Selection Pipeline for Direction-of-Arrival Estimation Using a Single Acoustic Vector Sensor

This paper presents a novel Non-negative Tensor Factorization (NTF) based approach to tracking and separation of moving sound sources, formulated in the Spherical Harmonic Domain (SHD). In particular, at first, we redefine an already existing Ambisonic NTF by introducing time-dependence into the Spatial Covariance Matrix (SCM) model. Next, we further extend the time-dependent SCM by incorporating a newly proposed NTF model of the spatial features, thereby introducing spatial components. To exploit the relationship between the positions of sound sources in adjacent time frames, resulting from the nat-urally occurring continuity of the movement itself, we impose local smoothness on time-dependent components of the spatial features. To this end, we propose a suitable posterior probability with Gibbs prior, and finally we derive the corresponding update rules. The experimental evaluation is based on first-order Ambisonic recordings of speech utterances and musical instruments in several scenarios with moving sources.

NTF of Spectral and Spatial Features for Tracking and Separation of Moving Sound Sources in Spherical Harmonic Domain

In adjacent sources scenarios, the low angular separation between active sources may degrade the performance of direction-of-arrival (DOA) estimation. In this work, we propose a slide-save based framework to address the problem of extracting multi-source DOAs for closely spaced sources. The basic idea is to identify the DOA estimates corresponding to the locally most dominant source within a sliding time-frequency (TF) window. Three different schemes are introduced to determine the critical DOA estimates in each TF window. The final DOAs are extracted using the retained DOA estimates by extending the histogram-based, clustering-based and Gaussian Mixture Model (GMM)-based multi-source DOA extraction methods. In addition, other intensity-based algorithms can also be incorporated into the proposed framework. Simulation results show that the proposed framework is effective to estimate multi-source DOAs in adjacent sources scenarios. 

A Slide-Save Based Framework for Multi-Source DOA Extraction with Closely Spaced Sources

The spatial nature of Ambisonics audio recordings makes them specially interesting for source localization and source separation tasks. Although existing proposals have already shown promising results, there is a lack of annotated databases, required for algorithm design, training and evaluation in this particular scenario. In this paper we present AmbiScaper, a tool for the automatic generation and annotation of reverberant Ambisonics sound scenes, published under an Open Source license to facilitate research reproducibility. As a use case, a database of annotated audio scenes has been created and published, along with an analysis with state-of-the-art sound localization algorithms.

Areeb Riaz

Papers

Adaptive blind moving source separation based on intensity vector statistics