Christine Evers – Christine Evers

“LOCATA Challenge-Evaluation Tasks and Measures”

By Christine Evers|2019-02-03T15:35:24+00:00September 20th, 2018|

Access:

International Workshop on Acoustic Signal Enhancement (IWAENC)

Authors:

Christine Evers, Heinrich W. Löllmann, Heinrich Mellmann, Alexander Schmidt, Hendrik Barfuss, Patrick A. Naylor, Walter Kellermann

Abstract:

Sound source localization and tracking algorithms provide estimates of the positional information about active sound sources in acoustic environments. Despite substantial advances and significant interest in the research community, a comprehensive benchmarking campaign of the various approaches using a common database of audio recordings has, to date, not been performed. The aim of the IEEE-AASP Challenge on sound source localization and tracking (LOCATA) is to objectively benchmark state-of-the-art localization and tracking algorithms using an open-access data corpus of recordings for scenarios typically encountered in audio and acoustic signal processing applications. The challenge tasks range from the localization of a single source with a static microphone array to tracking of multiple moving sources with a moving microphone array. This paper provides an overview of the challenge tasks, describes the performance measures used for evaluation of the LOCATA Challenge, and presents baseline results for the development dataset.

“DoA Reliability for Distributed Acoustic Tracking”

By Christine Evers|2018-08-10T10:19:30+00:00June 6th, 2018|

Access:

IEEE Signal Processing Letters

Supplemental Material of Mathematical Proofs

Authors:

Christine Evers, Emanuël A. P. Habets, Sharon Gannot, and Patrick A. Naylor

Abstract:

Distributed acoustic tracking estimates the trajectories of source positions using an acoustic sensor network. As it is often difficult to estimate the source-sensor range from individual nodes, the source positions have to be inferred from Direction of Arrival (DoA) estimates. Due to reverberation and noise, the sound field becomes increasingly diffuse with increasing source-sensor distance, leading to decreased DoA estimation accuracy. To distinguish between accurate and uncertain DoA estimates, this paper proposes to incorporate the Coherent-to-Diffuse Ratio as a measure of DoA reliability for single-source tracking. It is shown that the source positions therefore can be probabilistically triangulated by exploiting the spatial diversity of all nodes.

“The LOCATA Challenge Data Corpus for Acoustic Source Localization and Tracking“

By Christine Evers|2018-07-30T16:03:53+00:00May 29th, 2018|

Access:

Proceedings IEEE Sensor Array and Multichannel (SAM) Signal Processing Workshop 2018

Authors:

Heinrich W. Löllmann, Christine Evers, Alexander Schmidt, Heinrich Mellmann, Hendrik Barfuss, Patrick A. Naylor, and Walter Kellermann

Abstract:

Algorithms for acoustic source localization and tracking are essential for a wide range of applications such as personal assistants, smart homes, tele-conferencing systems, hearing aids, or autonomous systems. Numerous algorithms have been proposed for this purpose which, however, are not evaluated and compared against each other by using a common database so far. The IEEE-AASP Challenge on sound source localization and tracking (LOCATA) provides a novel, comprehensive data corpus for the objective benchmarking of state-of-the-art algorithms on sound source localization and tracking. The data corpus comprises six tasks ranging from the localization of a single static sound source with a static microphone array to the tracking of multiple moving speakers with a moving microphone array. It contains real-world multichannel audio recordings, obtained by hearing aids, microphones integrated in a robot head, a planar and a spherical microphone array in an enclosed acoustic environment, as well as positional information about the involved arrays and sound sources represented by moving human talkers or static loudspeakers.

“Acoustic SLAM”

By Christine Evers|2018-04-20T03:51:12+00:00April 13th, 2018|

Open Access:

IEEE Transactions on Audio, Speech and Language Processing

Authors:

Christine Evers and Patrick A. Naylor

Abstract:

An algorithm is presented that enables devices equipped with microphones, such as robots, to move within their environment in order to explore, adapt to and interact with sound sources of interest. Acoustic scene mapping creates a 3D representation of the positional information of sound sources across time and space. In practice, positional source information is only provided by Direction-of-Arrival (DoA) estimates of the source directions; the source-sensor range is typically difficult to obtain. DoA estimates are also adversely affected by reverberation, noise, and interference, leading to errors in source location estimation and consequent false DoA estimates. Moroever, many acoustic sources, such as human talkers, are not continuously active, such that periods of inactivity lead to missing DoA estimates. Withal, the DoA estimates are specified relative to the observer’s sensor location and orientation. Accurate positional information about the observer therefore is crucial. This paper proposes Acoustic Simultaneous Localization and Mapping (aSLAM), which uses acoustic signals to simultaneously map the 3D positions of multiple sound sources whilst passively localizing the observer within the scene map. The performance of aSLAM is analyzed and evaluated using a series of realistic simulations. Results are presented to show the impact of the observer motion and sound source localization accuracy.

IEEE-AASP Challenge on Acoustic Source Localization and Tracking (LOCATA)

By Christine Evers|2018-05-21T13:18:25+00:00February 22nd, 2018|

On behalf of the organising committee, I am pleased to announce the release of the development dataset for the IEEE-AASP Challenge on Acoustic Source Localization and Tracking (LOCATA).

The aim of this challenge is to provide researchers in the field of acoustic source localization and tracking the opportunity to benchmark their algorithms against competing approaches using a common data corpus that encompasses real multichannel recordings for different scenarios and microphone configurations. The dataset can be obtained from the LOCATA website http://www.locata-challenge.org.

The development dataset is intended to allow participants to familiarize themselves with and adapt their algorithms to the data corpus and evaluation framework. For this purpose, the development dataset contains the ground-truth positional data of all sources. For participation in the LOCATA challenge, participants submit the performance results of their algorithms applied to the evaluation dataset.

The LOCATA challenge outcome will be announced during a satellite workshop to be held at IWAENC 2018. Challenge participants submit to the LOCATA workshop a 4-page paper detailing the algorithmic framework of their submission(s). Papers submitted to the LOCATA challenge will be published on arXiv in the proceedings of the IEEE-AASP LOCATA Challenge. The proceedings aim to provide an overview of the practical aspects of the algorithmic frameworks submitted to LOCATA. Challenge participants are strongly encouraged to submit papers describing novel contributions, such as the proposal of new algorithms, in the form of regular papers to IWAENC in addition to participating in the LOCATA satellite workshop during IWAENC.

The current timetable is as follows:

February 16, 2018: Release of the development (Dev) data
April 16, 2018: Release of the evaluation (Eval) data
April 20, 2018: IWAENC regular paper deadline
June 1, 2018: LOCATA deadline for evaluation results
August 1, 2018: LOCATA paper deadline
September 20, 2018: LOCATA satellite workshop at IWAENC 2018 in Tokyo

“Optimized Self-Localization for SLAM in Dynamic Scenes using Probability Hypothesis Density Filters”

By Christine Evers|2018-01-16T21:42:37+00:00January 16th, 2018|

Open Access:

IEEE Transactions on Signal Processing

Authors:

Christine Evers and Patrick A. Naylor

Abstract:

In many applications, sensors that map the positions of objects in unknown environments are installed on dynamic platforms. As measurements are relative to the observer’s sensors, scene mapping requires accurate knowledge of the observer state. However, in practice, observer reports are subject to positioning errors. Simultaneous Localization and Mapping (SLAM) addresses the joint estimation problem of observer localization and scene mapping. State-of-the-art approaches typically use visual or optical sensors and therefore rely on static beacons in the environment to anchor the observer estimate. However, many applications involving sensors that are not conventionally used for SLAM are affected by highly dynamic scenes, such that the static world assumption is invalid. This paper proposes a novel approach for dynamic scenes, called GEneralized Motion (GEM)-SLAM. Based on Probability Hypothesis Density (PHD) filters, the proposed approach probabilistically anchors the observer state by fusing observer information inferred from the scene with reports of the observer motion. This paper derives the general, theoretical framework for GEM-SLAM and shows that it generalizes existing PHD-based SLAM algorithms. Simulations for a model-specific realization using range-bearing sensors and multiple moving objects highlight that GEM-SLAM achieves significant improvements over three benchmark algorithms.

CfP: Intl. Workshop on Acoustic Signal Enhancement (IWAENC), Tokyo, Japan, Sep 17-20, 2018

By Christine Evers|2018-01-16T13:42:12+00:00January 1st, 2018|

IWAENC2018_CFP

“Sparse parametric modeling of the early part of acoustic impulse responses”

By Christine Evers|2018-01-16T22:09:44+00:00October 26th, 2017|

IEEE Xplore Access:

Proc. European Signal Processing Conference (EUSIPCO)

Authors:

Constantinos Papayannis, Christine Evers and Patrick A. Naylor

Abstract:

Acoustic channels are typically described by their Acoustic Impulse Response (AIR) as a Moving Average (MA) process. Such AIRs are often considered in terms of their early and late parts, describing discrete reflections and the diffuse reverberation tail respectively. We propose an approach for constructing a sparse parametric model for the early part. The model aims at reducing the number of parameters needed to represent it and subsequently reconstruct from the representation the MA coefficients that describe it. It consists of a representation of the reflections arriving at the receiver as delayed copies of an excitation signal. The Time-Of-Arrivals of reflections are not restricted to integer sample instances and a dynamically estimated model for the excitation sound is used. We also present a corresponding parameter estimation method, which is based on regularized-regression and nonlinear optimization. The proposed method also serves as an analysis tool, since estimated parameters can be used for the estimation of room geometry, the mixing time and other channel properties. Experiments involving simulated and measured AIRs are presented, in which the AIR coefficient reconstruction-error energy does not exceed 11.4% of the energy of the original AIR coefficients. The results also indicate dimensionality reduction figures exceeding 90% when compared to a MA process representation.

Keynote Speech at UK Speech 2017

By Christine Evers|2018-01-16T01:29:06+00:00July 22nd, 2017|

I am delighted to be giving a keynote speech at UK Speech 2017 in Cambridge on “Acoustic Scene Mapping for Robot Audition”.

HSCMA Keynote slides online

By Christine Evers|2018-01-16T01:29:59+00:00July 22nd, 2017|

The slides for my keynote speech on “Bayesian Learning for Robot Audition” at HSCMA 2017 are now online on the website of the IEEE Audio and Acoustic Signal Processing Technical Committee.

About Christine Evers