Ecological acoustics perspective for content-based retrieval of environmental sounds

Authors:
Gerard Roma;Jordi Janer;Stefan Kersten;Mattia Schirosa;Perfecto Herrera;Xavier Serra
Affiliations:
Universitat Pompeu Fabra, Roc Boronat, Barcelona, Spain;Universitat Pompeu Fabra, Roc Boronat, Barcelona, Spain;Universitat Pompeu Fabra, Roc Boronat, Barcelona, Spain;Universitat Pompeu Fabra, Roc Boronat, Barcelona, Spain;Universitat Pompeu Fabra, Roc Boronat, Barcelona, Spain;Universitat Pompeu Fabra, Roc Boronat, Barcelona, Spain
Venue:
EURASIP Journal on Audio, Speech, and Music Processing - Special issue on environmental sound synthesis, processing, and retrieval
Year:
2010

Citing 6
Cited 5

Sounding Objects

IEEE MultiMedia
General sound classification and similarity in MPEG-7

Organised Sound
MPEG-7 Audio and Beyond: Audio Content Indexing and Retrieval

MPEG-7 Audio and Beyond: Audio Content Indexing and Retrieval
Nearest-neighbor automatic sound annotation with a WordNet taxonomy

Journal of Intelligent Information Systems - Special issue: Intelligent multimedia applications
Large-scale content-based audio retrieval from text queries

MIR '08 Proceedings of the 1st ACM international conference on Multimedia information retrieval
Environmental sound recognition with time-frequency audio features

IEEE Transactions on Audio, Speech, and Language Processing

Development of the database for environmental sound research and application (DESRA): design, functionality, and retrieval considerations

EURASIP Journal on Audio, Speech, and Music Processing - Special issue on environmental sound synthesis, processing, and retrieval
Towards equalization of environmental sounds using auditory-based features

Proceedings of the 6th Audio Mostly Conference: A Conference on Interaction with Sound
Active learning of custom sound taxonomies in unstructured audio data

Proceedings of the 2nd ACM International Conference on Multimedia Retrieval
ESSENTIA: an open-source library for sound and music analysis

Proceedings of the 21st ACM international conference on Multimedia
Freesound technical demo

Proceedings of the 21st ACM international conference on Multimedia

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we present a method to search for environmental sounds in large unstructured databases of user-submitted audio, using a general sound events taxonomy from ecological acoustics. We discuss the use of Support VectorMachines to classify sound recordings according to the taxonomy and describe two use cases for the obtained classificationmodels: a content-based web search interface for a large audio database and a method for segmenting field recordings to assist sound design.