Two-source acoustic event detection and localization: Online implementation in a Smart-room

Real-time processing is a requirement for many practical signal processing applications. In this work we implemented online 2-source acoustic event detection and localization algorithms in a Smart-room, a closed space equipped with multiple microphones. Acoustic event detection is based on HMMs that enable to process the input audio signal with very low latency; acoustic source localization is based on the SRP-PHAT localization method which is known to perform robustly in most scenarios. The experimental results from online tests show high recognition accuracy for most of acoustic events both isolated and overlapped with speech.

1. Introduction

Activity detection and description is a key functionality of perceptually aware interfaces working in collaborative human communication environments like meeting-rooms or classrooms. Actually, in the context of person-machine communication, computers involved in human communication activities have to meet certain requirements and be designed to have minimal possible awareness from the users. Consequently, there is a need of perceptual user interfaces which are multimodal and robust, and which use unobtrusive sensors that should sense the ongoing human activity. As human activity is reflected in a rich variety of acoustic events, either produced by the human body or by objects handled by humans, acoustic event detection (AED) may help to describe the human and social activity. Ringing telephones, clapping or laughter inside a speech discourse, a strong yawn in the middle of a lecture, knocks on doors, doors opening and closing, footsteps, or even the difference between one person speaking or more people speaking at the same time, are auditory cues that can be used to detect relevant events and state changes on meetings.