Binaural Scene Analysis with Multidimensional Statistical Filters

Spille, Constantin; Meyer, Bernd T.; Dietz, Mathias; Hohmann, Volker

doi:10.1007/978-3-642-37762-4_6

Cited by 7 publications

(6 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We give the state-space representation of the dynamical system that is being tracked but we do not go to any further details of RBPF. The algorithm proposed in [31] and the associated implementation has been used in [45] for tracking the azimuth angle of speakers in a similar setting.…”

Section: Acoustic Tracking Of Multiple Sound Sourcesmentioning

confidence: 99%

Separation of Moving Sound Sources Using Multichannel NMF and Acoustic Tracking

Nikunen

Virtanen

2018

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

In this paper we propose a method for separation of moving sound sources. The method is based on first tracking the sources and then estimation of source spectrograms using multichannel non-negative matrix factorization (NMF) and extracting the sources from the mixture by single-channel Wiener filtering. We propose a novel multichannel NMF model with time-varying mixing of the sources denoted by spatial covariance matrices (SCM) and provide update equations for optimizing model parameters minimizing squared Frobenius norm. The SCMs of the model are obtained based on estimated directions of arrival of tracked sources at each time frame. The evaluation is based on established objective separation criteria and using real recordings of two and three simultaneous moving sound sources. The compared methods include conventional beamforming and ideal ratio mask separation. The proposed method is shown to exceed the separation quality of other evaluated blind approaches according to all measured quantities. Additionally, we evaluate the method's susceptibility towards tracking errors by comparing the separation quality achieved using annotated ground truth source trajectories.

show abstract

Section: Acoustic Tracking Of Multiple Sound Sourcesmentioning

confidence: 99%

Separation of Moving Sound Sources Using Multichannel NMF and Acoustic Tracking

Nikunen

Virtanen

2018

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

show abstract

“…But since the position of sound sources is assumed to be stationary throughout the time interval over which the localization information is integrated, these methods are not considered in this chapter. For the application of binaural analysis in combination with particle filtering, see [70], this volume.…”

Section: Temporal Integrationmentioning

confidence: 99%

Binaural Localization and Detection of Speakers in Complex Acoustic Scenes

May

Par

Kohlrausch

2013

The Technology of Binaural Listening

View full text Add to dashboard Cite

“…We use the Monte Carlo sampling approach, i.e., particle filtering (Arulampalam et al, 2002) to track the state of simultaneously active voices. The method has already been used successfully in the context of speech tracking (Nix and Hohmann, 2007;Spille et al, 2013).…”

Section: Introductionmentioning

confidence: 99%

Making sense of periodicity glimpses in a prediction-update-loop—A computational model of attentive voice tracking

Luberadzka

Kayser

Hohmann

2022

The Journal of the Acoustical Society of America

View full text Add to dashboard Cite

JASA/Computational model of attentive voice tracking Humans are able to follow a given speaker even in challenging acoustic conditions.The perceptual mechanisms underlying this ability remain unclear. In this study, we present a computational model of attentive voice tracking, consisting of four main computational blocks: A) glimpsed feature extraction, B) foreground-background segregation, C) state estimation and D) top-down knowledge. Conceptually, the model brings together ideas related to auditory glimpses, vowel segregation and Bayesian inference. Algorithmically, it combines sparse periodicity feature extraction, sequential Monte Carlo sampling and probabilistic voice models. We evaluate the model by comparing it with the data obtained in the psychoacoustic task, which measured the ability to track of one of two competing voices with time-varying parameters (fundamental frequency (F 0) and first two formants (F 1, F 2)). We test three model versions, which differ in the type of information used in the segregation stage: version 1 uses oracle F 0, version 2 uses estimated F 0 and version 3 uses estimated F 0 and oracle F 1 and F 2. Version 1 outperforms human listeners, version 2 is not sufficient and version 3 is closest to explaining human performance.

show abstract

Binaural Scene Analysis with Multidimensional Statistical Filters

Cited by 7 publications

References 61 publications

Separation of Moving Sound Sources Using Multichannel NMF and Acoustic Tracking

Separation of Moving Sound Sources Using Multichannel NMF and Acoustic Tracking

Binaural Localization and Detection of Speakers in Complex Acoustic Scenes

Making sense of periodicity glimpses in a prediction-update-loop—A computational model of attentive voice tracking

Contact Info

Product

Resources

About