The Musical Avatar: a visualization of musical preferences by means of audio content description
Comunicació presentada a: AM '10: The 5th Audio Mostly Conference: A Conference on Interaction with Sound celebrat al setembre de 2010 a Piteå, Suècia. The music we like (i.e. our musical preferences) encodes and communicates key information about ourselves. Depicting such preferences in a cond...
Published in: | Proceedings of the 5th Audio Mostly Conference on A Conference on Interaction with Sound - AM '10 |
---|---|
Main Authors: | , , , , , |
Format: | Conference Object |
Language: | English |
Published: |
ACM Association for Computer Machinery
|
Subjects: | |
Online Access: | http://hdl.handle.net/10230/47005 https://doi.org/10.1145/1859799.1859813 |
id |
ftupompeufabra:oai:repositori.upf.edu:10230/47005 |
---|---|
record_format |
openpolar |
spelling |
ftupompeufabra:oai:repositori.upf.edu:10230/47005 2023-05-15T18:00:01+02:00 The Musical Avatar: a visualization of musical preferences by means of audio content description Haro Berois, Martín Xambó, Anna Fuhrmann, Ferdinand Bogdanov, Dmitry Gómez Gutiérrez, Emilia, 1975- Herrera Boyer, Perfecto, 1964- application/pdf http://hdl.handle.net/10230/47005 https://doi.org/10.1145/1859799.1859813 eng eng ACM Association for Computer Machinery AM '10: Proceedings of the 5th Audio Mostly Conference: A Conference on Interaction with Sound; 2010 Sep; Piteå, Sweden. New York: Association for Computing Machinery; 2010. p. 103-10 Haro M, Xambó A, Fuhrmann F, Bogdanov D, Gómez E, Herrera P. The Musical Avatar: a visualization of musical preferences by means of audio content description. In: AM '10: Proceedings of the 5th Audio Mostly Conference: A Conference on Interaction with Sound; 2010 Sep; Piteå, Sweden. New York: Association for Computing Machinery; 2010. p. 103-10. DOI:10.1145/1859799.1859813 http://hdl.handle.net/10230/47005 http://dx.doi.org/10.1145/1859799.1859813 © 2010 Association for Computing Machinery info:eu-repo/semantics/openAccess Music information research (MIR) User modeling Audio content analysis Semantic retrieval Music visualization info:eu-repo/semantics/conferenceObject info:eu-repo/semantics/acceptedVersion ftupompeufabra https://doi.org/10.1145/1859799.1859813 2021-08-03T23:20:07Z Comunicació presentada a: AM '10: The 5th Audio Mostly Conference: A Conference on Interaction with Sound celebrat al setembre de 2010 a Piteå, Suècia. The music we like (i.e. our musical preferences) encodes and communicates key information about ourselves. Depicting such preferences in a condensed and easily understandable way is very appealing, especially considering the current trends in social network communication. In this paper we propose a method to automatically generate, given a provided set of preferred music tracks, an iconic representation of a user's musical preferences -- the Musical Avatar. Starting from the raw audio signal we first compute over 60 low-level audio features. Then, by applying pattern recognition methods, we infer a set of semantic descriptors for each track in the collection. Next, we summarize these track-level semantic descriptors, obtaining a user profile. Finally, we map this collection-wise description to the visual domain by creating a humanoid cartoony character that represents the user's musical preferences. We performed a proof-of-concept evaluation of the proposed method on 11 subjects with promising results. The analysis of the users' evaluations shows a clear preference for avatars generated by the proposed semantic descriptors over avatars derived from neutral or randomly generated values. We also found a general agreement on the representativeness of the users' musical preferences via the proposed visualization strategy. Conference Object Piteå UPF Digital Repository (Universitat Pompeu Fabra, Barcelona) Proceedings of the 5th Audio Mostly Conference on A Conference on Interaction with Sound - AM '10 1 8 |
institution |
Open Polar |
collection |
UPF Digital Repository (Universitat Pompeu Fabra, Barcelona) |
op_collection_id |
ftupompeufabra |
language |
English |
topic |
Music information research (MIR) User modeling Audio content analysis Semantic retrieval Music visualization |
spellingShingle |
Music information research (MIR) User modeling Audio content analysis Semantic retrieval Music visualization Haro Berois, Martín Xambó, Anna Fuhrmann, Ferdinand Bogdanov, Dmitry Gómez Gutiérrez, Emilia, 1975- Herrera Boyer, Perfecto, 1964- The Musical Avatar: a visualization of musical preferences by means of audio content description |
topic_facet |
Music information research (MIR) User modeling Audio content analysis Semantic retrieval Music visualization |
description |
Comunicació presentada a: AM '10: The 5th Audio Mostly Conference: A Conference on Interaction with Sound celebrat al setembre de 2010 a Piteå, Suècia. The music we like (i.e. our musical preferences) encodes and communicates key information about ourselves. Depicting such preferences in a condensed and easily understandable way is very appealing, especially considering the current trends in social network communication. In this paper we propose a method to automatically generate, given a provided set of preferred music tracks, an iconic representation of a user's musical preferences -- the Musical Avatar. Starting from the raw audio signal we first compute over 60 low-level audio features. Then, by applying pattern recognition methods, we infer a set of semantic descriptors for each track in the collection. Next, we summarize these track-level semantic descriptors, obtaining a user profile. Finally, we map this collection-wise description to the visual domain by creating a humanoid cartoony character that represents the user's musical preferences. We performed a proof-of-concept evaluation of the proposed method on 11 subjects with promising results. The analysis of the users' evaluations shows a clear preference for avatars generated by the proposed semantic descriptors over avatars derived from neutral or randomly generated values. We also found a general agreement on the representativeness of the users' musical preferences via the proposed visualization strategy. |
format |
Conference Object |
author |
Haro Berois, Martín Xambó, Anna Fuhrmann, Ferdinand Bogdanov, Dmitry Gómez Gutiérrez, Emilia, 1975- Herrera Boyer, Perfecto, 1964- |
author_facet |
Haro Berois, Martín Xambó, Anna Fuhrmann, Ferdinand Bogdanov, Dmitry Gómez Gutiérrez, Emilia, 1975- Herrera Boyer, Perfecto, 1964- |
author_sort |
Haro Berois, Martín |
title |
The Musical Avatar: a visualization of musical preferences by means of audio content description |
title_short |
The Musical Avatar: a visualization of musical preferences by means of audio content description |
title_full |
The Musical Avatar: a visualization of musical preferences by means of audio content description |
title_fullStr |
The Musical Avatar: a visualization of musical preferences by means of audio content description |
title_full_unstemmed |
The Musical Avatar: a visualization of musical preferences by means of audio content description |
title_sort |
musical avatar: a visualization of musical preferences by means of audio content description |
publisher |
ACM Association for Computer Machinery |
url |
http://hdl.handle.net/10230/47005 https://doi.org/10.1145/1859799.1859813 |
genre |
Piteå |
genre_facet |
Piteå |
op_relation |
AM '10: Proceedings of the 5th Audio Mostly Conference: A Conference on Interaction with Sound; 2010 Sep; Piteå, Sweden. New York: Association for Computing Machinery; 2010. p. 103-10 Haro M, Xambó A, Fuhrmann F, Bogdanov D, Gómez E, Herrera P. The Musical Avatar: a visualization of musical preferences by means of audio content description. In: AM '10: Proceedings of the 5th Audio Mostly Conference: A Conference on Interaction with Sound; 2010 Sep; Piteå, Sweden. New York: Association for Computing Machinery; 2010. p. 103-10. DOI:10.1145/1859799.1859813 http://hdl.handle.net/10230/47005 http://dx.doi.org/10.1145/1859799.1859813 |
op_rights |
© 2010 Association for Computing Machinery info:eu-repo/semantics/openAccess |
op_doi |
https://doi.org/10.1145/1859799.1859813 |
container_title |
Proceedings of the 5th Audio Mostly Conference on A Conference on Interaction with Sound - AM '10 |
container_start_page |
1 |
op_container_end_page |
8 |
_version_ |
1766168932456071168 |