Abstract
Localizing the origin of a music piece around the world enables some interesting possibilities for geospatial music retrieval, for instance, location-aware music retrieval or recommendation for travelers or exploring non-Western music – a task neglected for a long time in music information retrieval (MIR). While previous approaches for the task of determining the origin of music either focused solely on exploiting the audio content or web resources, we propose a method that fuses features from both sources in a way that outperforms stand-alone approaches. To this end, we propose the use of block-level features inferred from the audio signal to model music content. We show that these features outperform timbral and chromatic features previously used for the task. On the other hand, we investigate a variety of strategies to construct web-based predictors from web pages related to music pieces. We assess different parameters for this kind of predictors (e.g., number of web pages considered) and define a confidence threshold for prediction. Fusing the proposed audio- and web-based methods by a weighted Borda rank aggregation technique, we show on a previously used dataset of music from 33 countries around the world that the median placing error can be reduced from \(1,\!815\) to 0 kilometers using K-nearest neighbor regression.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
- 2.
- 3.
- 4.
- 5.
Please note that the obvious query scheme “piece” (music) country does not perform well as it results in too many irrelevant pages about country music.
- 6.
Please further note that investigating queries in languages other than English is out of the scope of the work at hand, but will be addressed as part of future work.
References
Cheng, Z., Caverlee, J., Lee, K.: You are where you tweet: a content-based approach to geo-locating twitter users. In: Proceedings of CIKM, October 2010
de Borda, J.-C.: Mémoire sur les élections au scrutin. Histoire de l’Académie Royale des Sciences (1781)
Gómez, E., Herrera, P., Gómez-Martin, F.: Computational ethnomusicology: perspectives and challenges. J. New Music Res. 42(2), 111–112 (2013)
Govaerts, S., Duval, E.: A web-based approach to determine the origin of an artist. In: Proceedings of ISMIR, October 2009
Hauff, C., Houben, G.-J.: Placing Images on the world map: a microblog-based enrichment approach. In: Proceedings of SIGIR, August 2012
Kaminskas, M., Ricci, F., Schedl, M.: Location-aware music recommendation using auto-tagging and hybrid matching. In: Proceedings of RecSys, October 2013
Kinsella, S., Murdock, V., O’Hare, N.: “I’m eating a sandwich in Glasgow”: modeling locations with tweets. In: Proceedings of SMUC, October 2011
Knees, P., Schedl, M., Pohle, T.: A deeper look into web-based classification of music artists. In: Proceedings of LSAS, June 2008
Koenigstein, N., Shavitt, Y.: Song ranking based on piracy in peer-to-peer networks. In: Proceedings of ISMIR, October 2009
Koenigstein, N., Shavitt, Y., Tankel, T.: Spotting out emerging artists using geo-aware analysis of P2P query strings. In: Proceedings of KDD, August 2008
Liu, J., Inkpen, D.: Estimating user location in social media with stacked denoising auto-encoders. In: Proceedings of Vector Space Modeling for NLP, June 2015
Ripley, B.D.: Spatial Statistics. Wiley, New York (2004)
Schedl, M., Flexer, A., Urbano, J.: The neglected user in music information retrieval research. J. Intell. Inf. Syst. 41, 523–539 (2013)
Schedl, M., Schiketanz, C., Seyerlehner, K.: Country of origin determination via web mining techniques. In: Proceedings of AdMIRe, July 2010
Schedl, M., Schnitzer, D.: Hybrid retrieval approaches to geospatial music recommendation. In: Proceedings of SIGIR, July–August 2013
Schedl, M., Seyerlehner, K., Schnitzer, D., Widmer, G., Schiketanz, C.: Three web-based heuristics to determine a person’s or institution’s country of origin. In: Proceedings of SIGIR, July 2010
Serra, X.: Data gathering for a culture specific approach in MIR. In: Proceedings of AdMIRe, April 2012
Seyerlehner, K., Schedl, M., Knees, P., Sonnleitner, R.: A refined block-level feature set for classification, similarity and tag prediction. In: Extended Abstract MIREX, October 2009
Seyerlehner, K., Schedl, M., Sonnleitner, R., Hauger, D., Ionescu, B.: From improved auto-taggers to improved music similarity measures. In: Nürnberger, A., Stober, S., Larsen, B., Detyniecki, M. (eds.) AMR 2012. LNCS, vol. 8382, pp. 193–202. Springer, Heidelberg (2014)
Seyerlehner, K., Widmer, G., Pohle, T.: Fusing block-level features for music similarity estimation. In: Proceedings of DAFx, September 2010
Seyerlehner, K., Widmer, G., Schedl, M., Knees, P.: Automatic music tag classification based on block-level features. In: Proceedings of SMC, July 2010
Trevisiol, M., Jégou, H., Delhumeau, J., Gravier, G.: Retrieving geo-location of videos with a divide & conquer hierarchical multimodal approach. In: Proceedings of ICMR, April 2013
Tzanetakis, G., Cook, P.: MARSYAS: a framework for audio analysis. Organ. Sound 4, 169–175 (2000)
Workman, S., Souvenir, R., Jacobs, N.: Wide-area image geolocalization with aerial reference imagery. In: Proceedings of ICCV, December 2015
Yu, H., Xie, L., Sanner, S.: Views, Twitter-driven YouTube : beyond individual influencers. In: Proceedings of ACM Multimedia, November 2014
Zhou, F., Claire, Q., King, R.D.: Predicting the geographical origin of music. In: Proceedings of ICDM, December 2014
Acknowledgments
This research is supported by the Austrian Science Fund (FWF): P25655. The authors would further like to thank Klaus Seyerlehner for his implementation of the block-level feature extraction framework and Ross D. King and the reviewers for their valuable comments on the manuscript.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Schedl, M., Zhou, F. (2016). Fusing Web and Audio Predictors to Localize the Origin of Music Pieces for Geospatial Retrieval. In: Ferro, N., et al. Advances in Information Retrieval. ECIR 2016. Lecture Notes in Computer Science(), vol 9626. Springer, Cham. https://doi.org/10.1007/978-3-319-30671-1_24
Download citation
DOI: https://doi.org/10.1007/978-3-319-30671-1_24
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-30670-4
Online ISBN: 978-3-319-30671-1
eBook Packages: Computer ScienceComputer Science (R0)