Unified auditory functions based on Bayesian topic model

Existing auditory functions for robots such as sound source localization and separation have been implemented in a cascaded framework whose overall performance may be degraded by any failure in its subsystems. These approaches often require a careful and environment-dependent tuning for each subsystems to achieve better performance. This paper presents a unified framework for sound source localization and separation where the whole system is integrated as a Bayesian topic model. This method improves both localization and separation with a common configuration under various environments by iterative inference using Gibbs sampling. Experimental results from three environments of different reverberation times confirm that our method outperforms state-of-the-art sound source separation methods, especially in the reverberant environments, and shows localization performance comparable to that of the existing robot audition system.

Authors

• Takuma Otsuka
• Katsuhiko Ishiguro
• Hiroshi Sawada
• Hiroshi G. Okuno

Keywords

• Time frequency analysis
• Vectors
• Microphones
• Robot sensing systems
• Arrays
• Bayesian Model
• Topic Modeling
• Bayesian Topic Model
• Gibbs Sampling
• Source Separation
• Sound Source
• Sound Localization
• Careful Tuning
• Reverberation Time
• Spectroscopic
• Posterior Probability
• Latent Variables
• Gamma Distribution
• Channel Signal
• Anechoic Chamber
• Inference Procedure
• Short-time Fourier Transform
• Separation Performance
• Frequency Bins
• Separation Problem
• Steering Vector
• Microphone Array
• Latent Dirichlet Allocation
• Dirichlet Distribution
• Teleoperator
• Wishart Distribution
• Auditory Environment
• Conjugate Prior
• Sampling Convergence