Talk
in
Workshop: Machine Learning for Audio Signal Processing (ML4Audio)

Multi-Speaker Localization Using Convolutional Neural Network Trained with Noise

Soumitro Chakrabarty ⋅ Emanuël Habets

2017 Talk
in
Workshop: Machine Learning for Audio Signal Processing (ML4Audio)

Project Page

Abstract

The problem of multi-speaker localization is formulated as a multi-class multi-label classification problem, which is solved using a convolutional neural network (CNN) based source localization method. Utilizing the common assumption of disjoint speaker activities, we propose a novel method to train the CNN using synthesized noise signals. The proposed localization method is evaluated for two speakers and compared to a well-known steered response power method.

Chat is not available.