You are here

Speaker Localization

This demo shows the FBK Speaker Localization and Tracking real-time system based on a distributed microphone network. The system is based on the measurement in the space of a score that represents the plausibility that a sound source is in a given 3D point in space (Global Coherence Field, derived from a consolidated technique, ITC-irst 1992).

Head orientation is then obtained by using the Oriented Global Coherence Field, a score that represents the plausibility that a sound source is in a given position and it is oriented in a given direction. This technique represents the state-of-the-art in head orientation.

The system is based on reversed 7 T-shaped microphone arrays installed on the four walls of the room. In this demo (that leads to a 2D location) we used 7 pairs of far-field microphones numbered from T0 to T6.

Possible applications: smart rooms, automatic camera-tracking for video conferencing, lectures, meetings, surveillance, domotics, robotics, speech enhancement, distant-talking speech recognition, acoustic scene analysis for any other applicative context.

Localization and orientation estimation of acoustic sources, Distributed Microphone Network