Acoustic source separation of convolutive mixtures based on intensity vector statistics

Date

2008-05-01

Author

Günel Kılıç, Banu
Hacıhabiboğlu, Hüseyin

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

136
views

0
downloads

Various techniques have previously been proposed for the separation of convolutive mixtures. These techniques can be classified as stochastic, adaptive, and deterministic. Stochastic methods are computationally expensive since they require an iterative process for the calculation of the demixing filters based on a separation criterion that usually assumes that the source signals are statistically independent. Adaptive methods, such as the adaptive beamformers, also exploit signal properties in order to optimize a multichannel filter structure. However, these algorithms need initialization and time to converge. Deterministic methods, on the other hand, provide a closed-form solution based on the deterministic aspects of the problem, such as the channel characteristics and the source directions. This paper presents a technique that exploits the intensity vector statistics to achieve a nearly closed-form solution for the separation of the convolutive mixtures as recorded with a coincident microphone array. No assumptions are made on the signals, but it is assumed that the source directions are known a priori. Directivity functions based on von Mises functions are designed for beamforming depending on the circular statistics of the calculated intensity vectors. Numerical evaluation results were presented for various speech and instrument sounds and source positions in two reverberant rooms.

Subject Keywords

Array processing, B-format, Beamforming, Circular statistics, Coincident microphone array, Convolutive mixtures, Intensity, Source separation

URI

https://hdl.handle.net/11511/32309

Journal

IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING

DOI

https://doi.org/10.1109/tasl.2008.918967

Collections

Graduate School of Informatics, Article

Suggestions

OpenMETU
Core

Intensity vector direction exploitation for exhaustive blind source separation of convolutive mixtures Günel Kılıç, Banu; Hacıhabiboğlu, Hüseyin (2009-04-19) 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 th...
Thin-film microextraction coupled to LC-ESI-MS/MS for determination of quaternary ammonium compounds in water samples Boyacı, Ezel; Pawliszyn, Janusz (Springer Science and Business Media LLC, 2014-01-01) The dual nature of the quaternary ammonium compounds, having permanently charged hydrophilic quaternary ammonium heads and long-chain hydrophobic tails, makes the sample preparation step and analysis of these compounds challenging. A high-throughput method based on thin-film solid-phase microextraction (SPME) and liquid chromatography mass spectrometry was developed for simultaneous quantitative analysis of nine benzylic and aliphatic quaternary ammonium compounds. Chromatographic separation and detection o...
Cyclic behavior of Adapazarı silt and clay mixtures Pekcan, Onur; Çetin, Kemal Önder; Bakır, Bahadır Sadık (null; 2004-01-07) Within the confines of this paper, it is intended to understand cyclic behavior of clayey silt and silty clay mixtures, sampled from Adapazarı–Turkey. For this purpose, series of cyclic triaxial tests were performed on the samples retrieved from five selected soil sites, where buildings founded on these soils exhibited significant foundation displacements. After consolidating samples to 0.50 atm. cyclic loads were applied to simulate 1999 Kocaeli-Turkey earthquake shaking. Volumetric strains were recorded b...
Triazine herbicide imprinted monolithic column for capillary electrochromatography Asir, Suleyman; Derazshamshir, Ali; YILMAZ, FATMA; DENİZLİ, ADİL (2015-12-01) Trietazine was selectively separated from aqueous solution containing the competitor molecule cyanazine, which is similar in size and shape to the template molecule. Structural features of the molecularly imprinted column were figured out by SEM. The influence of the mobile-phase composition, applied electrical field, and pH of the mobile phase on the recognition of trietazine by the imprinted monolithic polymer has been evaluated, and the imprint effect in the trietazine-imprinted monolithic polymer was de...
Thermal characterization and kinetic analysis of sara fractions of crude oils by TGA and DSC methods Gül, Kıymet Gizem; Kök, Mustafa Verşan; Department of Petroleum and Natural Gas Engineering (2011) In this thesis, four different crude oil samples and their saturate, aromatic and resin fractions were analyzed by two different thermoanalytical methods, thermogravimetric analysis (TGA) and differential scanning calorimetry (DSC). The experiments were performed at three different heating rates (5, 10 and 15 °C/min) under air atmosphere. Same gas flow rate and same pressure were applied to all samples. The aim is to determine the kinetic analysis and combustion behavior of crude oils and their fractions an...

Citation Formats

B. Günel Kılıç and H. Hacıhabiboğlu, “Acoustic source separation of convolutive mixtures based on intensity vector statistics,” IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, pp. 748–756, 2008, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/32309.