TY - GEN
T1 - Fast query by example of environmental sounds via robust and efficient cluster-based indexing
AU - Xue, Jiachen
AU - Wichern, Gordon
AU - Thornburg, Harvey
AU - Spanias, Andreas
PY - 2008
Y1 - 2008
N2 - There has been much recent progress in the technical infrastructure necessary to continuously characterize and archive all sounds, or more precisely auditory streams, that occur within a given space or human life. Efficient and intuitive access, however, remains a considerable challenge. In specifically musical domains, i.e., melody retrieval, query-by-example (QBE) has found considerable success in accessing music that matches a specific query. We propose an extension of the QBE paradigm to the broad class of natural and environmental sounds, which occur frequently in continuous recordings. We explore several cluster-based indexing approaches, namely non-negative matrix factorization (NMF) and spectral clustering to efficiently organize and quickly retrieve archived audio using the QBE paradigm. Experiments on a test database compare the performance of the different clustering algorithms in terms of recall, precision, and computational complexity. Initial results indicate significant improvements over both exhaustive search schemes and traditional K-means clustering, and excellent overall performance in the example-based retrieval of environmental sounds.
AB - There has been much recent progress in the technical infrastructure necessary to continuously characterize and archive all sounds, or more precisely auditory streams, that occur within a given space or human life. Efficient and intuitive access, however, remains a considerable challenge. In specifically musical domains, i.e., melody retrieval, query-by-example (QBE) has found considerable success in accessing music that matches a specific query. We propose an extension of the QBE paradigm to the broad class of natural and environmental sounds, which occur frequently in continuous recordings. We explore several cluster-based indexing approaches, namely non-negative matrix factorization (NMF) and spectral clustering to efficiently organize and quickly retrieve archived audio using the QBE paradigm. Experiments on a test database compare the performance of the different clustering algorithms in terms of recall, precision, and computational complexity. Initial results indicate significant improvements over both exhaustive search schemes and traditional K-means clustering, and excellent overall performance in the example-based retrieval of environmental sounds.
KW - Acoustic signal analysis
KW - Clustering methods
KW - Database query processing
KW - Hidden Markov models
UR - http://www.scopus.com/inward/record.url?scp=51449089882&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=51449089882&partnerID=8YFLogxK
U2 - 10.1109/ICASSP.2008.4517532
DO - 10.1109/ICASSP.2008.4517532
M3 - Conference contribution
AN - SCOPUS:51449089882
SN - 1424414849
SN - 9781424414840
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 5
EP - 8
BT - 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP
T2 - 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP
Y2 - 31 March 2008 through 4 April 2008
ER -