Estimation of propagation delays using orientation histograms for anechoic blind source separation

Yamashita, Jun; Tatsuta, S.; Hirai, Yukio

doi:10.1109/ijcnn.2004.1380956

Cited by 6 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sparsity-based algorithms, such as the Degenerate Unmixing Estimation Technique (DUET), depend on completely different aspects. The Spatial signature of sources and the multipath characteristics of the reverberant environment are exploited to perform deterministic sparsity-based source separation (Van Der Veen, 1998;Shindo and Hirai, 2002;Yamashita et al, 2004). DUET exploits relative amplitude and delay differences between the microphones to cluster similar time-frequency (T-F) components (Rickard, 2007).…”

Section: Related Workmentioning

confidence: 99%

Adaptive blind moving source separation based on intensity vector statistics

Riaz

Shi

Kondoz

2019

Speech Communication

View full text Add to dashboard Cite

This paper presents a novel approach to blind moving source separation by detecting, tracking and separating speakers in real-time using intensity vector direction (IVD) statistics. It updates unmixing system parameters swiftly in order to deal with the time-variant mixing parameters. Denoising is carried out to extract reliable speaker estimates using von-Mises modeling of the IVD measurements in space and IIR filtering of the IVD distribution in time. Peaks in the IVD distribution are assigned location expectation values to check for consistency, and consequently high location expectation peaks are declared as active speakers. The location expectation algorithm caters for natural pauses during speech delivery. Speaker movements are tracked by spatial isolation of the detected peaks using time-variant regions of interest. As a result, the proposed moving source separation system is capable of blindly detecting, tracking and separating moving speakers. A real-time demonstration has been developed with the proposed system pipeline, allowing users to listen to active speakers in any desired combination. The system has an advantage of using a small coincident microphone array to separate any number of moving sources utilising the first order Ambisonics signals while assuming source signals to be W-disjoint orthogonal. Being nearly closed-form, the proposed system does not require convergence or initialization of parameters.

show abstract

Section: Related Workmentioning

confidence: 99%

Adaptive blind moving source separation based on intensity vector statistics

Riaz

Shi

Kondoz

2019

Speech Communication

View full text Add to dashboard Cite

show abstract

“…ABF techniques utilize spatial selectivity to suppress the interferences and improve the capture of the target source. Another group of the BSS techniques, which can be called as deterministic, utilise solely the deterministic aspects of the problem, such as the directions of the sources or the multipath characteristics [5,6,7]. As these pieces of information are not available for the blind separation problem, the performance of the algorithms are limited by the accuracy of their estimations.…”

Section: Introductionmentioning

confidence: 99%

Intensity vector direction exploitation for exhaustive blind source separation of convolutive mixtures

Günel

Hacıhabiboğlu

Kondoz

2009

2009 IEEE International Conference on Acoustics, Speech and Signal Processing

View full text Add to dashboard Cite

This article presents a technique that uses the intensity vector direction exploitation (IVDE) method for exhaustive separation of convolutive mixtures. While only a four-element compact sensor array is used, multiple channels for all possible source directions are produced by exhaustive separation. Singular value decomposition (SVD) is then applied to determine the signal subspace and the directions of the local maxima of the signal energy. This information is then used to select the channels containing the individual sources. While the original IVDE method requires the prior knowledge of the directions of sources for separation, the present method eliminates this need and achieves fully blind separation. Performing SVD at a post-processing stage also improves the sound quality. The method has been tested for convolutive mixtures of up to four sources and typical separation performances are given.

show abstract

Dynamic blind source separation based on source-direction prediction

Wei

Wang

2016

Neurocomputing

View full text Add to dashboard Cite

Estimation of propagation delays using orientation histograms for anechoic blind source separation

Cited by 6 publications

References 13 publications

Adaptive blind moving source separation based on intensity vector statistics

Adaptive blind moving source separation based on intensity vector statistics

Intensity vector direction exploitation for exhaustive blind source separation of convolutive mixtures

Dynamic blind source separation based on source-direction prediction

Contact Info

Product

Resources

About