DocumentCode :
2574841
Title :
Unifying semantic and content-based approaches for retrieval of environmental sounds
Author :
Wichern, Gordon ; Thornburg, Harvey ; Spanias, Andreas
Author_Institution :
Arts, Media & Eng., Arizona State Univ., Tempe, AZ, USA
fYear :
2009
fDate :
18-21 Oct. 2009
Firstpage :
13
Lastpage :
16
Abstract :
Creating a database of user-contributed recordings allows sounds to be linked not only by the semantic tags and labels applied to them, but also to other sounds with similar acoustic characteristics. Of paramount importance in navigating these databases are the problems of retrieving similar sounds using text or sound-based queries, and automatically annotating unlabeled sounds. We propose an integrated system, which can be used for text-based retrieval of unlabeled audio, content-based query-by-example, and automatic annotation. To this end, we introduce an ontological framework where sounds are connected to each other based on a measure of perceptual similarity, while words and sounds are connected by optimizing link weights given user preference data. Results on a freely available database of environmental sounds contributed and labeled by non-expert users, demonstrate effective average precision scores for both the text-based retrieval and annotation tasks.
Keywords :
acoustic signal processing; audio databases; audio signal processing; content-based retrieval; hidden Markov models; ontologies (artificial intelligence); optimisation; query processing; text analysis; acoustic signal analysis; audio database creation; automatic annotation; content-based query-by-example; content-based retrieval; environmental sound-based query; hidden Markov model; integrated system; link weight optimization; ontological framework; perceptual similarity measure; text-based retrieval; unifying semantic tag approach; unlabeled audio; user preference data; user-contributed recording; Acoustic applications; Audio databases; Conferences; Content based retrieval; Hidden Markov models; Information retrieval; Internet; Music information retrieval; Navigation; Ontologies; Acoustic signal analysis; Clustering methods; Database query processing; Hidden Markov models;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Applications of Signal Processing to Audio and Acoustics, 2009. WASPAA '09. IEEE Workshop on
Conference_Location :
New Paltz, NY
ISSN :
1931-1168
Print_ISBN :
978-1-4244-3678-1
Electronic_ISBN :
1931-1168
Type :
conf
DOI :
10.1109/ASPAA.2009.5346493
Filename :
5346493
Link To Document :
بازگشت