Paper Info
Title
Sound-event recognition with a companion humanoid
Abstract
In this paper we address the problem of recognizing everyday sound events in indoor environments with a consumer robot. Sounds are represented in the spectro-temporal domain using the stabilized auditory image (SAI) representation. The SAI is well suited for representing pulse-resonance sounds and has the interesting property of mapping a time-varying signal into a fixed-dimension feature vector space. This allows us to map the sound recognition problem into a supervised classification problem and to adopt a variety of classifications schemes. We present a complete system that takes as input a continuous signal, splits it into significant isolated sounds and noise, and classifies the isolated sounds using a catalogue of learned sound-event classes. The method is validated with a large set of audio data recorded with a humanoid robot in a house. Extended experiments show that the proposed method achieves state-of-the-art recognition scores with a twelve-class problem, while requiring extremely limited memory space and moderate computing power. A first real-time embedded implementation in a consumer robot show its ability to work in real conditions.
Year
DOI
Venue
2012
10.1109/HUMANOIDS.2012.6651506
Humanoid Robots
Keywords
Field
DocType
audio signal processing,humanoid robots,image representation,robot vision,signal classification,vectors,SAI representation,audio data recording,catalogue,companion humanoid,consumer robot,fixed-dimension feature vector space,humanoid robot,indoor environments,learned sound-event classes,pulse-resonance sound representation,sound-event recognition,spectro-temporal domain,stabilized auditory image representation,supervised classification problem,time-varying signal mapping,twelve-class problem
Sound recognition,Computer vision,Feature vector,Continuous signal,Computer science,Image representation,Speech recognition,Artificial intelligence,Audio signal processing,Robot,Event recognition,Humanoid robot
Conference
ISSN
Citations 
PageRank 
2164-0572
11
0.71
References 
Authors
9
4
Name
Order
Citations
PageRank
Maxime Janvier1211.41
Xavier Alameda-Pineda223228.24
Laurent Girin347353.76
Radu Horaud42776261.99