Pattern Classification (2nd Edition)
Pattern Classification (2nd Edition)
Blind separation of speech mixtures via time-frequency masking
IEEE Transactions on Signal Processing
Batch and Online Underdetermined Source Separation Using Laplacian Mixture Models
IEEE Transactions on Audio, Speech, and Language Processing
| Hi-index | 0.00 |
This paper proposes a method for estimating the direction of arrival (DOA) of multiple source signals for an underdetermined situation, where the number of sources N exceeds the number of sensors M (M驴N). Some DOA estimation methods have already been proposed for underdetermined cases. However, since most of them restrict their microphone array arrangements, their DOA estimation ability is limited to a 2-dimensional plane. To deal with an underdetermined case where sources are distributed arbitrarily, we propose a method that can employ a 2- or 3-dimensional sensor array. Our new method employs the source sparseness assumption to handle an underdetermined case. Our formulation with the sensor coordinate vectors allows us to employ arbitrarily arranged sensors easily. We obtained promising experimental results for 2-dimensionally distributed sensors and sources 3脳4, 3脳5 (#sensors 脳 #speech sources), and for 3-dimensional case with 4脳5 in a room (reverberation time (RT) of 120 ms). We also investigate the DOA estimation performance under several reverberant conditions.