摘要: Human-robot communication is often faced with the difficult problem of interpreting ambiguous auditory data. For example, acoustic signals perceived by a humanoid its on-board microphones contain mix sounds such as speech, music, electronic devices, all in presence attenuation and reverberations. In this paper we propose novel method, based on generative probabilistic model active binaural hearing, allowing robot to robustly perform sound-source separation localization. We show how interaural spectral cues can be used within constrained mixture specifically designed capture richness data gathered two mounted onto human-like artificial head. describe detail EM algorithm, analyse initialization, speed convergence complexity, assess performance both simulated real
acm.org
sci-hub.se 参考文章(26)
Antoine Deleforge, Radu Horaud, A latently constrained mixture model for audio source separation and localization international conference on latent variable analysis and signal separation. ,vol. 7191, pp. 372- 379 ,(2012) , 10.1007/978-3-642-28551-6_46
Anatoly Zhigljavsky, Antanasz Zilinskas, None, Stochastic Global Optimization ,(2007)
Pierre Comon, Christian Jutten, Handbook of Blind Source Separation: Independent Component Analysis and Applications Academic Press. pp. 831- ,(2010)
N. Roman, DeLiang Wang, Binaural Tracking of Multiple Moving Sources IEEE Transactions on Audio, Speech, and Language Processing. ,vol. 16, pp. 728- 739 ,(2008) , 10.1109/TASL.2008.918978
Makoto Otani, Tatsuya Hirahara, Shiro Ise, Numerical study on source-distance dependency of head-related transfer functions. Journal of the Acoustical Society of America. ,vol. 125, pp. 3253- 3261 ,(2009) , 10.1121/1.3111860
O. Yilmaz, S. Rickard, Blind separation of speech mixtures via time-frequency masking IEEE Transactions on Signal Processing. ,vol. 52, pp. 1830- 1847 ,(2004) , 10.1109/TSP.2004.828896
Fakheredine Keyrouz, Werner Maier, Klaus Diepold, Robotic Localization and Separation of Concurrent Sound Sources using Self-Splitting Competitive Learning 2007 IEEE Symposium on Computational Intelligence in Image and Signal Processing. pp. 340- 345 ,(2007) , 10.1109/CIISP.2007.369192
Vasil Khalidov, Florence Forbes, Radu Horaud, Conjugate mixture models for clustering multimodal data Neural Computation. ,vol. 23, pp. 517- 557 ,(2011) , 10.1162/NECO_A_00074
J. Allen, Short term spectral analysis, synthesis, and modification by discrete Fourier transform IEEE Transactions on Acoustics, Speech, and Signal Processing. ,vol. 25, pp. 235- 238 ,(1977) , 10.1109/TASSP.1977.1162950
Gilles Celeux, Gérard Govaert, A Classification EM algorithm for clustering and two stochastic versions Computational Statistics & Data Analysis. ,vol. 14, pp. 315- 332 ,(1992) , 10.1016/0167-9473(92)90042-E