TY - GEN
T1 - Automatic audio tagging using covariate shift adaptation
AU - Wichern, Gordon
AU - Yamada, Makoto
AU - Thornburg, Harvey
AU - Sugiyama, Masashi
AU - Spanias, Andreas
PY - 2010
Y1 - 2010
N2 - Automatically annotating or tagging unlabeled audio files has several applications, such as database organization and recommender systems. We are interested in the case where the system is trained using clean high-quality audio files, butmost of the files that need to be automatically tagged during the test phase are heavily compressed and noisy, for instance if they were captured on a mobile device. In this situation we assume the audio files follow a covariate shift model in the acoustic feature space, i.e., the feature distributions are different in the training and test phases, but the conditional distribution of labels given features remains unchanged. Our method uses a specially designed audio similarity measure as input to a set of weighted logistic regressors, which attempt to alleviate the influence of covariate shift. Results on a freely available database of sound files contributed and labeled by non-expert users, demonstrate effective automatic tagging performance.
AB - Automatically annotating or tagging unlabeled audio files has several applications, such as database organization and recommender systems. We are interested in the case where the system is trained using clean high-quality audio files, butmost of the files that need to be automatically tagged during the test phase are heavily compressed and noisy, for instance if they were captured on a mobile device. In this situation we assume the audio files follow a covariate shift model in the acoustic feature space, i.e., the feature distributions are different in the training and test phases, but the conditional distribution of labels given features remains unchanged. Our method uses a specially designed audio similarity measure as input to a set of weighted logistic regressors, which attempt to alleviate the influence of covariate shift. Results on a freely available database of sound files contributed and labeled by non-expert users, demonstrate effective automatic tagging performance.
KW - Acoustic signal analysis
KW - Database query processing
KW - Importance
KW - KLIEP
UR - http://www.scopus.com/inward/record.url?scp=78049412206&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=78049412206&partnerID=8YFLogxK
U2 - 10.1109/ICASSP.2010.5495973
DO - 10.1109/ICASSP.2010.5495973
M3 - Conference contribution
AN - SCOPUS:78049412206
SN - 9781424442966
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 253
EP - 256
BT - 2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010
Y2 - 14 March 2010 through 19 March 2010
ER -