1. Two-microphone multi-speaker localization based on a Laplacian Mixture Model
- Author
-
David Cuadra Martínez, Maximo Cobos, and Jose J. Lopez
- Subjects
Microphone array ,Disjointness ,Microphone ,Laplacian Mixture Model ,Real environments ,Time frequency ,DOA estimation ,A-Laplacian ,Speaker localization ,Artificial Intelligence ,TEORIA DE LA SEÑAL Y COMUNICACIONES ,Coherence (signal processing) ,Laplacian mixture models ,Speech signals ,Pre-selected ,Electrical and Electronic Engineering ,Mathematics ,Laplace transform ,business.industry ,Applied Mathematics ,Direction of arrival ,Laplace transforms ,Pattern recognition ,DOA estimates ,Mixture model ,Microphone arrays ,Time–frequency analysis ,Computational Theory and Mathematics ,Mixtures ,Signal Processing ,Computer Vision and Pattern Recognition ,Artificial intelligence ,Statistics, Probability and Uncertainty ,Expectation-maximization algorithms ,Microphones ,business ,Laplace operator ,Algorithms - Abstract
A method for multiple speaker localization using a two-microphone array is presented. Based on the disjointness property of speech signals in the time-frequency (TF) domain, the proposed approach models the distribution of Direction-Of-Arrival (DOA) estimates in the TF plane using a Laplacian Mixture Model (LMM). Reliable DOA estimates are pre-selected using a coherence-based criterion before fitting the model by means of the Expectation-Maximization (EM) algorithm. Results using public available data show the capability of the method to successfully detect the DOA of several sources in real environments. © 2010 Elsevier Inc. All rights reserved., This work was supported by the Ministry of Education and Science under the projects TEC2006-13883-C04-01 and TEC2009-14414-C03-01
- Published
- 2011
- Full Text
- View/download PDF