Skip to yearly menu bar Skip to main content


Poster

Latent Gaussian Activity Propagation: Using Smoothness and Structure to Separate and Localize Sounds in Large Noisy Environments

Daniel D. Johnson · Daniel Gorelik · Ross E Mawhorter · Kyle Suver · Weiqing Gu · Steven Xing · Cody Gabriel · Peter Sankhagowit

Room 517 AB #112

Keywords: [ Graphical Models ] [ Gaussian Processes ] [ Latent Variable Models ] [ Denoising ] [ Signal Processing ] [ Audio and Speech Processing ] [ Source Separation ]


Abstract:

We present an approach for simultaneously separating and localizing multiple sound sources using recorded microphone data. Inspired by topic models, our approach is based on a probabilistic model of inter-microphone phase differences, and poses separation and localization as a Bayesian inference problem. We assume sound activity is locally smooth across time, frequency, and location, and use the known position of the microphones to obtain a consistent separation. We compare the performance of our method against existing algorithms on simulated anechoic voice data and find that it obtains high performance across a variety of input conditions.

Live content is unavailable. Log in and register to view live content