This note presents a system that learns expressive and idiosyncratic gesture variations for gesture-based interaction. The system is used as an interaction technique in a music conducting scenario where gesture variations drive music articulation. A simple model based on Gaussian Mixture Modeling is used to allow the user to configure the system by providing variation examples. The system performance and the influence of user musical expertise is evaluated in a user study, which shows that the model is able to learn idiosyncratic variations that allow users to control articulation, with better performance for users with musical expertise.
JF - CHI - Human Factors in Computing Systems PB - ACM Press CY - San Jose, CA ER - TY - CONF T1 - Modeling Loudness Variations in Ensemble Performance T2 - 2nd International Conference on New Music Concepts (ICNMC 2016) Y1 - 2016 A1 - Gadermaier, Thassilo A1 - Grachten, Maarten A1 - Cancino-Chacon, Carlos Eduardo JF - 2nd International Conference on New Music Concepts (ICNMC 2016) PB - ABEditore CY - Treviso, Italy ER - TY - CONF T1 - A Personality-based Adaptive System for Visualizing Classical Music Performances T2 - Proceedings of the 7th ACM Multimedia Systems Conference (MMSys) Y1 - 2016 A1 - Markus Schedl A1 - Mark Melenhorst A1 - Cynthia C.S. Liem A1 - Agustín Martorell A1 - Óscar Mayor A1 - Marko Tkalčič JF - Proceedings of the 7th ACM Multimedia Systems Conference (MMSys) CY - Klagenfurt, Austria ER - TY - CONF T1 - Personalized Retrieval and Browsing of Classical Music and Supporting Multimedia Material T2 - Proceedings of the ACM International Conference on Multimedia Retrieval (ICMR) Y1 - 2016 A1 - Marko Tkalčič A1 - Markus Schedl A1 - Cynthia C.S. Liem A1 - Mark Melenhorst JF - Proceedings of the ACM International Conference on Multimedia Retrieval (ICMR) CY - New York, USA ER - TY - CONF T1 - Using Instagram Picture Features to Predict Users' Personality T2 - Proceedings of the 22nd International Conference on MultiMedia Modeling (MMM 2016) Y1 - 2016 A1 - Ferwerda, Bruce A1 - Schedl, Markus A1 - Tkalčič, Marko JF - Proceedings of the 22nd International Conference on MultiMedia Modeling (MMM 2016) CY - Miami, USA ER - TY - CONF T1 - Artificial Intelligence in the Concertgebouw T2 - Proceedings of the International Joint Conference on Artificial Intelligence Y1 - 2015 A1 - Andreas Arzt A1 - H. Frostel A1 - Th. Gadermaier A1 - M. Gasser A1 - G. Widmer A1 - M. Grachten JF - Proceedings of the International Joint Conference on Artificial Intelligence CY - Buenos Aires, Argentina ER - TY - CONF T1 - Classical Music on the Web - User Interfaces and Data Representations T2 - Proceedings of the 16th International Society for Music Information Retrieval Conference, {ISMIR} 2015, Málaga, Spain, October 26-30, 2015 Y1 - 2015 A1 - Martin Gasser A1 - Andreas Arzt A1 - Thassilo Gadermaier A1 - Maarten Grachten A1 - Gerhard Widmer JF - Proceedings of the 16th International Society for Music Information Retrieval Conference, {ISMIR} 2015, Málaga, Spain, October 26-30, 2015 UR - http://ismir2015.uma.es/articles/123_Paper.pdf ER - TY - CONF T1 - Comparative Analysis of Orchestral Performance Recordings: An Image-Based Approach T2 - 16th International Society for Music Information Retrieval Conference Y1 - 2015 A1 - Cynthia C. S. Liem A1 - Alan Hanjalic JF - 16th International Society for Music Information Retrieval Conference CY - Málaga, Spain ER - TY - CHAP T1 - Contextual set-class analysis T2 - Computational Music Analysis Y1 - 2015 A1 - Martorell, Agustín A1 - Gómez, Emilia ED - Meredith, David JF - Computational Music Analysis PB - Springer CY - Heidelberg ER - TY - CONF T1 - Correlations Between Musical Descriptors and Emotions Recognized in Beethoven’s Eroica T2 - Ninth Triennial Conference of the European Society for the Cognitive Sciences of Music (ESCOM) Y1 - 2015 A1 - Erika S. Trent A1 - Emilia Gómez KW - classical music KW - emotion KW - music description KW - music information retrieval KW - personalization AB -Investigations on music and emotion have identified broad musical elements that influence emotions recognized by listeners, such as timbre, rhythm, melody, and harmony. Not many studies have studied the correlation between quantifiable musical descriptors and their associated emotions; furthermore, only few studies have focused on how listeners’ demographic and musical backgrounds influence the emotion they recognize. In this preliminary study, participants rated how strongly they recognized the six GEMS emotions (transcendence, peacefulness, power, joyful activation, tension, and sadness) while listening to excerpts from Beethoven’s Eroica. Musical descriptors (loudness, brightness, noisiness, tempo/rhythm, harmony, and timbre) were also extracted from each excerpt. Results indicate significant correlations between emotional ratings and musical descriptors, notably positive correlations between key clarity and peacefulness/joyful activation ratings, and negative correlations between key clarity and tension/sadness ratings. Key clarity refers to the key strength associated to the best key candidate; as such, these results suggest that listeners recognize positive emotions in music with a straightforward key, whereas listeners recognize negative emotions in music with a less clear sense of key. The second part of the study computed correlations between demographics and emotional ratings, to determine whether people of similar demographic and musical backgrounds recognized similar emotions. The results indicate that na{\"ıve listeners (i.e. younger subjects, and subjects with less frequent exposure to classical music) experienced more similar emotions from the same musical excerpts than did other subjects. Our findings contribute to developing a quantitative understanding of how musical descriptors, and listeners’ backgrounds, correlate with emotions recognized by listeners.
JF - Ninth Triennial Conference of the European Society for the Cognitive Sciences of Music (ESCOM) CY - Manchester, UK UR - http://phenicx.upf.edu/system/files/publications/0168TrentGomez-ESCOM2015.pdf ER - TY - CONF T1 - An evaluation of score descriptors combined with non-linear models of expressive dynamics in music T2 - Proceedings of the 18th International Conference on Discovery Science (DS 2015) Y1 - 2015 A1 - Cancino Chacón, C. E. A1 - M. Grachten JF - Proceedings of the 18th International Conference on Discovery Science (DS 2015) PB - Springer CY - Banff, Canada ER - TY - CONF T1 - Flexible Score Following: The Piano Music Companion and Beyond T2 - Proceedings of the Vienna Talk on Music Acoustics Y1 - 2015 A1 - Andreas Arzt A1 - Goebl, W. A1 - Widmer, G. JF - Proceedings of the Vienna Talk on Music Acoustics ER - TY - CONF T1 - Improving Music Recommendations with a Weighted Factorization of the Tagging Activity T2 - Proceedings of the 16th International Society for Music Information Retrieval Conference (ISMIR) Y1 - 2015 A1 - Andreu Vall A1 - Marcin Skowron A1 - Peter Knees A1 - Markus Schedl JF - Proceedings of the 16th International Society for Music Information Retrieval Conference (ISMIR) CY - Malaga, Spain ER - TY - CONF T1 - Improving score-informed source separation for classical music through note refinement T2 - 16th International Society for Music Information Retrieval (ISMIR) Conference. Y1 - 2015 A1 - Marius Miron A1 - Julio José Carabias A1 - Jordi Janer JF - 16th International Society for Music Information Retrieval (ISMIR) Conference. CY - Malaga ER - TY - CONF T1 - On the Influence of User Characteristics on Music Recommendation T2 - Proceedings of the 37th European Conference on Information Retrieval (ECIR 2015) Y1 - 2015 A1 - Markus Schedl A1 - David Hauger A1 - Katayoun Farrahi A1 - Marko Tkalčič JF - Proceedings of the 37th European Conference on Information Retrieval (ECIR 2015) CY - Vienna, Austria ER - TY - CONF T1 - Iron Maiden while jogging, Debussy for dinner? - An analysis of music listening behavior in context T2 - Proceedings of the 21st International Conference on MultiMedia Modeling (MMM 2015) Y1 - 2015 A1 - Michael Gillhofer A1 - Markus Schedl JF - Proceedings of the 21st International Conference on MultiMedia Modeling (MMM 2015) CY - Sydney, Australia ER - TY - CONF T1 - I-Vectors for Timbre-Based Music Similarity and Music Artist Classification T2 - Proceedings of the 16th International Society for Music Information Retrieval Conference (ISMIR) Y1 - 2015 A1 - Hamid Eghbal-zadeh A1 - Bernhard Lehner A1 - Markus Schedl A1 - Gerhard Widmer JF - Proceedings of the 16th International Society for Music Information Retrieval Conference (ISMIR) CY - Malaga, Spain ER - TY - CONF T1 - Listener-aware Music Recommendation from Sensor and Social Media Data T2 - Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2015) Y1 - 2015 A1 - Markus Schedl JF - Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2015) CY - Porto, Portugal ER - TY - CONF T1 - Listener-aware Music Search and Recommendation T2 - Proceedings of the 6th International Workshop on Mining Ubiquitous and Social Environments (MUSE 2015) Y1 - 2015 A1 - Markus Schedl JF - Proceedings of the 6th International Workshop on Mining Ubiquitous and Social Environments (MUSE 2015) CY - Porto, Portugal ER - TY - THES T1 - Making Tabletops Useful with Applications, Frameworks and Multi-Tasking Y1 - 2015 A1 - Carles F. Julià KW - Applications KW - Collaboration KW - Frameworks KW - HCI KW - interaction KW - Multi-Tasking KW - Shared interfaces KW - tabletop AB -The progressive appearance of affordable tabletop technology and devices urges human-computer interaction researchers to provide the necessary methods to make this kind of devices the most useful to their users. Studies show that tabletops have distinctive characteristics that can be specially useful to solve some types of problems, but this potential is arguably not yet translated into real-world applications. We theorize that the important components that can transform those systems into useful tools are application frameworks that take into account the devices affordances, a third party application ecosystem, and multi-application systems supporting concurrent multitasking. In this dissertation we approach these key components: First, we explore the distinctive affordances of tabletops, with two cases: TurTan, a tangible programming language in the education context, and SongExplorer, a music collection browser for large databases. Next, in order to address the difficulty of building such applications in a way that they can exploit these affordances, we focus on software frameworks to support the tabletop application making process, with two different approaches: ofxTableGestures, targeting programmers, and MTCF, designed for music and sound artists. Finally, recognizing that making useful applications is just one part of the problem, we focus on a fundamental issue of multi-application tabletop systems: the difficulty to support multi-user concurrent multitasking with third-party applications. After analyzing the possible approaches, we present GestureAgents, a content-based distributed application-centric disambiguation mechanism and its implementation, which solves this problem in a generic fashion, being also useful to other shareable interfaces, including uncoupled ones.
PB - Universitat Pompeu Fabra CY - Barcelona ER - TY - Generic T1 - Mass Media Musical Meaning: Opportunities from the Collaborative Web T2 - 11th International Symposium on Computer Music Multidisciplinary Research (CMMR) Y1 - 2015 A1 - Cynthia C. S. Liem KW - collaborative web resources KW - cultural context KW - data science KW - mass media KW - music information retrieval KW - musicology KW - narrative elements KW - text retrieval AB -In the digital domain, music is usually studied from a positivist viewpoint, focusing on general ’objective’ music descriptors. In this work, we strive to put music in a more social and cultural context, looking into ways to unify data analysis methods with thoughts from the humanities on musical meaning and signi ficance. More speci fically, we investigate whether information in collaborative web resources on movie plot narratives and folksonomic song tags is capable of revealing common associations between these two. Reported initial fi ndings suggest this is indeed the case, which opens opportunities for further work in this area, cross-disciplinary collaborations, and novel contextually oriented music information retrieval application scenarios.
JF - 11th International Symposium on Computer Music Multidisciplinary Research (CMMR) CY - Plymouth, UK ER - TY - CONF T1 - Melody extraction by means of a source-filter model and pitch contour characterization (MIREX 2015) T2 - Music Information Retrieval Evaluation eXchange (MIREX) Y1 - 2015 A1 - Bosch, J. A1 - Gómez, E. JF - Music Information Retrieval Evaluation eXchange (MIREX) ER - TY - CONF T1 - Melovizz: A Web-based tool for Score-Informed Melody Extraction Visualization T2 - ISMIR (Late Breaking Demo) Y1 - 2015 A1 - Bosch, J. A1 - Mayor, O. A1 - Gómez, E. JF - ISMIR (Late Breaking Demo) ER - TY - THES T1 - Multifaceted Approaches to Music Information Retrieval T2 - Department of Intelligent Systems, Faculty of Electrical Engineering, Mathematics and Computer Science Y1 - 2015 A1 - Cynthia C. S. Liem JF - Department of Intelligent Systems, Faculty of Electrical Engineering, Mathematics and Computer Science PB - Delft University of Technology CY - Delft VL - PhD SN - 9789462992382 UR - http://dx.doi.org/10.4233/uuid:e8a04372-4c55-4b5f-9bc3-aaab73fe649d ER - TY - CONF T1 - Music Retrieval and Recommendation – A Tutorial Overview T2 - Proceedings of the 38th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) Y1 - 2015 A1 - Peter Knees A1 - Markus Schedl JF - Proceedings of the 38th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) CY - Santiago, Chile ER - TY - JOUR T1 - Personality Correlates for Digital Concert Program Notes JF - UMAP 2015, Springer LNCS 9146 Y1 - 2015 A1 - Tkalčič, Marko A1 - Ferwerda, Bruce A1 - Hauger, David A1 - Schedl, Markus KW - classical music KW - digital program notes KW - personality ER - TY - CONF T1 - Personality & Emotional States: Understanding Users’ Music Listening Needs T2 - Extended Proceedings of the 22nd International Conference on User Modeling, Adaptation and Personalization (UMAP 2015) Y1 - 2015 A1 - Ferwerda, Bruce A1 - Schedl, Markus A1 - Tkalčič, Marko JF - Extended Proceedings of the 22nd International Conference on User Modeling, Adaptation and Personalization (UMAP 2015) CY - Dublin, Ireland ER - TY - CONF T1 - Personality Traits Predict Music Taxonomy Preferences T2 - Proceedings of the 33rd Annual ACM Conference Extended Abstracts on Human Factors in Computing Systems - CHI EA '15 Y1 - 2015 A1 - Ferwerda, Bruce A1 - Yang, Emily A1 - Schedl, Markus A1 - Tkalčič, Marko JF - Proceedings of the 33rd Annual ACM Conference Extended Abstracts on Human Factors in Computing Systems - CHI EA '15 SN - 9781450331463 UR - http://dx.doi.org/10.1145/2702613.2732754 http://dl.acm.org/citation.cfm?doid=2702613.2732754 ER - TY - CONF T1 - PHENICX: Innovating the Classical Music Experience T2 - Proceedings of the IEEE International Conference on Multimedia and Expo (ICME 2015) Y1 - 2015 A1 - Cynthia C. S. Liem A1 - Emilia Gómez A1 - Markus Schedl JF - Proceedings of the IEEE International Conference on Multimedia and Expo (ICME 2015) CY - Torino, Italy ER - TY - CONF T1 - Put the Concert Attendee in the Spotlight. A User-Centered Design and Development Approach for Classical Concert Applications T2 - 16th International Society for Music Information Retrieval Conference Y1 - 2015 A1 - Mark S. Melenhorst A1 - Cynthia C. S. Liem JF - 16th International Society for Music Information Retrieval Conference CY - Málaga, Spain UR - http://ismir2015.uma.es/articles/67_Paper.pdf ER - TY - CONF T1 - Real-time Music Tracking using Multiple Performances as a Reference T2 - Proceedings of the International Society for Music Information Retrieval Conference (ISMIR) Y1 - 2015 A1 - Andreas Arzt A1 - Widmer, G. JF - Proceedings of the International Society for Music Information Retrieval Conference (ISMIR) ER - TY - CONF T1 - A Tablet App to Enrich the Live and Post-Live Experience of Classical Concerts T2 - Proceedings of the 3rd International Workshop on Interactive Content Consumption (WSICC) at TVX 2015 Y1 - 2015 A1 - Mark S. Melenhorst A1 - Ron van der Sterren A1 - Andreas Arzt A1 - Martorell, Agustín A1 - Cynthia C. S. Liem JF - Proceedings of the 3rd International Workshop on Interactive Content Consumption (WSICC) at TVX 2015 ER - TY - CONF T1 - Tailoring Music Recommendations to Users by Considering Diversity, Mainstreaminess, and Novelty T2 - Proceedings of the 38th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) Y1 - 2015 A1 - Markus Schedl A1 - David Hauger JF - Proceedings of the 38th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) CY - Santiago, Chile ER - TY - CONF T1 - Timbral Modeling for Music Artist Recognition Using I-vectors T2 - Proceedings of the 23rd European Signal Processing Conference (EUSIPCO 2015) Y1 - 2015 A1 - Hamid Eghbal-zadeh A1 - Markus Schedl A1 - Gerhard Widmer JF - Proceedings of the 23rd European Signal Processing Conference (EUSIPCO 2015) CY - Nice, France ER - TY - CONF T1 - Towards Personalizing Classical Music Recommendations T2 - SoMeRA 2015: Proceedings of the Second International Workshop on Social Media Retrieval and Analysis Y1 - 2015 A1 - Markus Schedl JF - SoMeRA 2015: Proceedings of the Second International Workshop on Social Media Retrieval and Analysis CY - Atlantic City, USA ER - TY - CONF T1 - Web-based visualizations and acoustic rendering for multimodal data from orchestra performances using repovizz T2 - WAC - 1st Web Audio Conference Y1 - 2015 A1 - Mayor, O. KW - Technical Demo AB -In the demo a set of fully working web-based prototypes developed in the context of the EU FP7 PHENICX Project (http://phenicx.upf.edu) will be presented. The Phenicx project is about innovating the classical music experience providing them with a multimodal, multi-perspective and multilayer interactive engagement, before, during and after the concert. In this demo we present some prototypes that are related with the post concert experience.
We have recorded a set of classical pieces performed by top level orchestras, including some data modalities like multi-channel audio, video, motion capture sensors, midi and text. Once all data streams have been time-synchronized, we have performed the following analysis on the data:
- Low-level and high-level audio descriptors for each individual audio source
- Description of conductor gestures based on the motion capture sensors
- Score to performance alignment
- Audio source separation
- Musical structure analysis of the performed piece
Then all these data is uploaded to the repovizz web repository (repovizz.upf.edu) that allows visualization and sharing of the data over the network. A set of customized web-based visualizations have been designed to build the prototypes that will be shown in this demo. Multimodal data streams are accessed on-line using the repovizz web API and html5 is used for the visualizations of the multimodal data and descriptors extracted from the performances. The web-audio API is used to handle the audio rendering in the client to mix between the different audio channels obtained from the different recorded audio sources or from the automatic isolation of instruments performed in the analysis step.
The visualizations available include (all web-based):
- Scrolling piano roll visualization of the musical score while audio is playing
- Orchestra layout visualization showing instrument activity and loudness while playing audio
- Audio focus to hear individual instruments playing alone
- Multi-perspective video angle selection during the concert
- 3D render of the conductor body
Here is a live example of the orchestra layout visualization including the isolation of instruments as an example of one of the prototypes that will be shown during the demo: http://repovizz.upf.edu/phenicx
Video showing some of the repovizz orchestra visualizations developed in the context of PHENICX: https://www.youtube.com/watch?v=c7pmDvkKY7A#t=168
The musical conductor metaphor has been broadly used in the design of musical interfaces where users control the expressive aspects of the performance imitating the movements of conductors. Most of the times, there are predefined rules for the interaction to which users have to adapt. Other works have focused on studying the relation between conductors' gestures and the resulting performance of the orchestra. Here, we study how different subjects move when asked to conduct on top of classical music excerpts, with a focus on the influence of the beat of the performance. Twenty-five subjects were asked to conduct on top of three classical music fragments and recorded with a commercial depth-sense camera. We evaluated predicted beats using ground truth annotations from score-performance alignment by an expert musicologist and a modified F-measure that is able to account for different tendencies on beat anticipation across subjects. The results show that these tendencies can be used for possible improvements in the design of conducting musical interfaces in terms of user adaptation.
JF - Proceedings of the 2014 International Workshop on Movement and Computing PB - ACM CY - Paris, France SN - 978-1-4503-2814-2 UR - http://doi.acm.org/10.1145/2617995.2618016 ER - TY - CONF T1 - Bridging the Audio-Symbolic Gap: The Discovery of Repeated Note Content Directly from Polyphonic Music Audio T2 - 53rd AES Conference on Semantic Audio Y1 - 2014 A1 - Collins, Tom A1 - Sebastian Böck A1 - Krebs, Florian A1 - Widmer, Gerhard JF - 53rd AES Conference on Semantic Audio CY - London, UK ER - TY - CONF T1 - The Complete Classical Music Companion V0.9 T2 - 53rd AES Conference on Semantic Audio Y1 - 2014 A1 - Andreas Arzt A1 - Sebastian Böck A1 - Flossmann, Sebastian A1 - Frostel, Harald A1 - Gasser, Martin A1 - Widmer, Gerhard JF - 53rd AES Conference on Semantic Audio CY - London, UK ER - TY - CONF T1 - Dynamics in Music Conducting: A Computational Comparative Study Among Subjects T2 - Proceedings of the International Conference on New Interfaces for Musical Expression Y1 - 2014 A1 - Álvaro Sarasúa A1 - Enric Guaus AB -Many musical interfaces have used the musical conductor metaphor, allowing users to control the expressive aspects of a performance by imitating the gestures of conductors. In most of them, the rules to control these expressive aspects are predefined and users have to adapt to them. Other works have studied conductors' gestures in relation to the performance of the orchestra. The goal of this study is to analyze, following the path initiated by this latter kind of works, how simple motion capture descriptors can explain the relationship between the loudness of a given performance and the way in which different subjects move when asked to impersonate the conductor of that performance. Twenty-five subjects were asked to impersonate the conductor of three classical music fragments while listening to them. The results of different linear regression models with motion capture descriptors as explanatory variables show that, by studying how descriptors correlate to loudness differently among subjects, different tendencies can be found and exploited to design models that better adjust to their expectations.
JF - Proceedings of the International Conference on New Interfaces for Musical Expression PB - Goldsmiths, University of London CY - London, United Kingdom UR - http://nime2014.org/proceedings/papers/464_paper.pdf ER - TY - CONF T1 - Exploiting Instrument-wise Playing/Non-Playing Labels for Score Synchronization of Symphonic Music T2 - Proceedings of the 15th International Society for Music Information Retrieval Conference Y1 - 2014 A1 - Alessio Bazzica A1 - Cynthia C. S. Liem A1 - Hanjalic, Alan AB - Score synchronization with an audio-visual recording of a symphonic music performance is usually done by solving an audio-to-MIDI alignment problem. In this paper we investigate what role visual channel can have in this process. In particular, we focus on the possibility to represent both the score and the performance by the information about what instrument is active at a given time stamp. More specifically, we investigate to what extent instrument-level 'play' (P) and 'non-play' (NP) labels are informative in the synchronization process. After introducing the P/NP-based representation of the music piece, both at the score and performance level, we define an efficient way of computing the distance between the two representations, which serves as input for the synchronization step based on dynamic time warping. In parallel with assessing the effectiveness of the proposed representation, we also study its robustness when missing and/or erroneous labels occur. Our experimental results show that P/NP-based music piece representation is informative for performance-to-score synchronization and may benefit the existing audio-only approaches. JF - Proceedings of the 15th International Society for Music Information Retrieval Conference CY - Taipei, Taiwan ER - TY - CONF T1 - Genre-based Analysis of Social Media Data on Music Listening Behavior T2 - Proceedings of the 1st ACM International Workshop on Internet-Scale Multimedia Management (ISMM 2014) Y1 - 2014 A1 - Markus Schedl A1 - Marko Tkalčič JF - Proceedings of the 1st ACM International Workshop on Internet-Scale Multimedia Management (ISMM 2014) CY - Orlando, FL, USA ER - TY - JOUR T1 - Hierarchical multi-scale set-class analysis JF - Journal of Mathematics and Music Y1 - 2014 A1 - Martorell, Agustín A1 - Gómez, Emilia UR - http://dx.doi.org/10.1080/17459737.2014.906072 ER - TY - JOUR T1 - The impact of hesitation, a social signal, on a user’s quality of experience in multimedia content retrieval JF - Springer Multimedia Tools and Applications Y1 - 2014 A1 - Vodlan, Tomaż A1 - Tkalčič, Marko A1 - Košir, Andrej KW - computer interaction KW - hesitation KW - human KW - social signals KW - video-on-demand UR - http://link.springer.com/10.1007/s11042-014-1933-2 ER - TY - CONF T1 - Impact of Listening Behavior on Music Recommendation T2 - Proceedings of the 15th International Society for Music Information Retrieval Conference (ISMIR 2014) Y1 - 2014 A1 - Katayoun Farrahi A1 - Markus Schedl A1 - Andreu Vall A1 - David Hauger A1 - Marko Tkalčič JF - Proceedings of the 15th International Society for Music Information Retrieval Conference (ISMIR 2014) CY - Taipei, Taiwan ER - TY - Generic T1 - Improved musical onset detection with convolutional neural networks T2 - Proceedings of the 39th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2014) Y1 - 2014 A1 - Jan Schlüter A1 - Sebastian Böck JF - Proceedings of the 39th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2014) ER - TY - CONF T1 - Location-Aware Music Artist Recommendation T2 - Proceedings of the 20th International Conference on MultiMedia Modeling (MMM 2014) Y1 - 2014 A1 - Markus Schedl A1 - Dominik Schnitzer JF - Proceedings of the 20th International Conference on MultiMedia Modeling (MMM 2014) CY - Dublin, Ireland ER - TY - Generic T1 - Melody extraction in symphonic classical music: a comparative study of mutual agreement between humans and algorithms T2 - 9th Conference on Interdisciplinary Musicology – CIM14 Y1 - 2014 A1 - Bosch, J. A1 - Gómez, E. JF - 9th Conference on Interdisciplinary Musicology – CIM14 CY - Berlin ER - TY - CONF T1 - Mobile Music Genius: Reggae at the Beach, Metal on a Friday Night? T2 - Proceedings of the 2014 ACM International Conference on Multimedia Retrieval (ICMR) Y1 - 2014 A1 - Markus Schedl A1 - Georg Breitschopf A1 - Bogdan Ionescu JF - Proceedings of the 2014 ACM International Conference on Multimedia Retrieval (ICMR) CY - Glasgow, UK ER - TY - JOUR T1 - Music Information Retrieval: Recent Developments and Applications JF - {Foundations and Trends in Information Retrieval} Y1 - 2014 A1 - Markus Schedl A1 - Emilia Gómez A1 - Julián Urbano VL - 8 ER - TY - CONF T1 - PatternViewer: An Application for Exploring Repetitive and Tonal Structure T2 - Proceedings of the 15th International Society for Music Information Retrieval Conference (ISMIR 2014) Y1 - 2014 A1 - Ali Nikrang A1 - Tom Collins A1 - Gerhard Widmer JF - Proceedings of the 15th International Society for Music Information Retrieval Conference (ISMIR 2014) CY - Taipei, Taiwan ER - TY - CONF T1 - The Piano Music Companion T2 - Proceedings of the Conference on Prestigious Applications of Intelligent Systems (PAIS) Y1 - 2014 A1 - Andreas Arzt A1 - Sebastian Böck A1 - Flossmann, S. A1 - Frostel, H. A1 - Gasser, M. A1 - Cynthia C. S. Liem A1 - Widmer, G. JF - Proceedings of the Conference on Prestigious Applications of Intelligent Systems (PAIS) ER - TY - CONF T1 - Predicting expressive dynamics in piano performances using neural networks T2 - Proceedings of the 15th International Conference on Music Information Retrieval Y1 - 2014 A1 - Van Herwaarden, S A1 - Grachten, M A1 - De Haas, W. B. JF - Proceedings of the 15th International Conference on Music Information Retrieval CY - Taipei, Taiwan ER - TY - Generic T1 - Set-class surface analysis: a hierarchical multi-scale approach T2 - 7th International Workshop on Machine Learning and Music (MML'14) Y1 - 2014 A1 - Martorell, Agustín JF - 7th International Workshop on Machine Learning and Music (MML'14) CY - Barcelona ER - TY - CONF T1 - Social Media and Classical Music? – A first analysis within the PHENICX project: “Performances as Highly Enriched aNd Interactive Concert eXperiences” T2 - SoMeRA'14: Proceedings of the First International Workshop on Social Media Retrieval and Analysis Y1 - 2014 A1 - Markus Schedl JF - SoMeRA'14: Proceedings of the First International Workshop on Social Media Retrieval and Analysis CY - Gold Coast, Australia ER - TY - CONF T1 - SoMeRA 2014: Social Media Retrieval and Analysis Workshop T2 - Proceedings of the 37th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) Y1 - 2014 A1 - Markus Schedl A1 - Peter Knees A1 - Jialie Shen JF - Proceedings of the 37th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) CY - Gold Coast, Australia ER - TY - Generic T1 - Systematic multi-scale set-class analysis T2 - 15th International Society for Music Information Retrieval Conference, Taipei, Taiwan Y1 - 2014 A1 - Martorell, Agustín A1 - Gómez, Emilia JF - 15th International Society for Music Information Retrieval Conference, Taipei, Taiwan CY - Taipei (Taiwan) ER - TY - CONF T1 - Systematic set-class surface analysis: a hierarchical multi-scale approach T2 - 8th European Music Analysis Conference, Leuven, Belgium Y1 - 2014 A1 - Martorell, Agustín JF - 8th European Music Analysis Conference, Leuven, Belgium CY - Leuven (Belgium) ER - TY - CONF T1 - Tempo- and Transposition-invariant Identification of Piece and Score Position T2 - Proceedings of the International Society for Music Information Retrieval Conference (ISMIR) Y1 - 2014 A1 - Andreas Arzt A1 - Widmer, G. A1 - Sonnleitner, R. JF - Proceedings of the International Society for Music Information Retrieval Conference (ISMIR) ER - TY - CONF T1 - To Post or Not to Post: The Effects of Persuasive Cues and Group Targeting Mechanisms on Posting Behavior T2 - Proceedings of the 6th ASE International Conference on Social Computing (SocialCom 2014) Y1 - 2014 A1 - Bruce Ferwerda A1 - Markus Schedl A1 - Marko Tkalčič JF - Proceedings of the 6th ASE International Conference on Social Computing (SocialCom 2014) CY - Stanford, USA ER - TY - CONF T1 - User Geospatial Context for Music Recommendation in Microblogs T2 - Proceedings of the 37th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) Y1 - 2014 A1 - Markus Schedl A1 - Andreu Vall A1 - Katayoun Farrahi JF - Proceedings of the 37th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) CY - Gold Coast, Australia ER - TY - CONF T1 - Using Social Media Mining for Estimating Theory of Planned Behaviour Parameters T2 - Proceedings of the 2nd Workshop on Emotions and Personality in Personalized Services (EMPIRE 2014) Y1 - 2014 A1 - Bruce Ferwerda A1 - Markus Schedl JF - Proceedings of the 2nd Workshop on Emotions and Personality in Personalized Services (EMPIRE 2014) CY - Aalborg, Denmark ER - TY - CONF T1 - Using Social Media Mining for Estimating Theory of Planned Behaviour Parameters T2 - Proceedings of the 2nd Workshop on Emotions and Personality in Personalized Services (EMPIRE 2014) Y1 - 2014 A1 - Marko Tkalčič A1 - Bruce Ferwerda A1 - Markus Schedl A1 - Cynthia C. S. Liem A1 - Mark S. Melenhorst A1 - Ante Odić A1 - Andrej Košir JF - Proceedings of the 2nd Workshop on Emotions and Personality in Personalized Services (EMPIRE 2014) CY - Aalborg, Denmark ER - TY - CONF T1 - What Really Moves Us in Music: Expressivity as a Challenge to Semantic Audio Research T2 - 53rd AES Conference on Semantic Audio Y1 - 2014 A1 - Widmer, Gerhard JF - 53rd AES Conference on Semantic Audio CY - London, UK ER - TY - CONF T1 - Ameliorating Music Recommendation: Integrating Music Content, Music Context, and User Context for Improved Music Retrieval and Recommendation T2 - Proceedings of the 11th International Conference on Advances in Mobile Computing & Multimedia (MoMM 2013) Y1 - 2013 A1 - Markus Schedl JF - Proceedings of the 11th International Conference on Advances in Mobile Computing & Multimedia (MoMM 2013) CY - Vienna, Austria ER - TY - CONF T1 - Automatic alignment of music performances with structural differences T2 - Proceedings of the 14th International Society for Music Information Retrieval Conference Y1 - 2013 A1 - Grachten, Maarten A1 - Gasser, Martin A1 - Andreas Arzt A1 - Widmer, Gerhard AB -Both in interactive music listening, and in music performance research, there is a need for automatic alignment of different recordings of the same musical piece. This task is challenging, because musical pieces often contain parts that may or may not be repeated by the performer, possibly leading to structural differences between performances (or between performance and score). The most common alignment method, dynamic time warping (DTW), cannot handle structural differences adequately, and existing approaches to deal with structural differences explicitly rely on the annotation of ``break points'' in one of the sequences. We propose a simple extension of the Needleman-Wunsch algorithm to deal effectively with structural differences, without relying on annotations. We evaluate several audio features for alignment, and show how an optimal value can be found for the cost-parameter of the alignment algorithm. A single cost value is demonstrated to be valid across different types of music. We demonstrate that our approach yields roughly equal alignment accuracies compared to DTW in the absence of structural differences, and superior accuracies when structural differences occur.
Body movement has received increasing attention in music technology research during the last years. Some new mu- sical interfaces make use of gestures to control music in a meaningful and intuitive way. A typical approach is to use the orchestra conducting paradigm, in which the computer that generates the music would be a virtual orchestra con- ducted by the user. However, although conductors’ gestures are complex and their meaning can vary depending on the musical context, this context-dependency is still to explore. We propose a method to study context-dependency of body and facial gestures of conductors in orchestral classical mu- sic based on temporal clustering of gestures into actions, followed by an analysis of the evolution of audio features after action occurrences. For this, multi-modal data (audio, video, motion capture) will be recorded in real live concerts and rehearsals situations using unobtrusive techniques.
JF - ACM Multimedia CY - Barcelona ER - TY - CONF T1 - Enhanced peak picking for onset detection with recurrent neural networks T2 - Proceedings of the 6th International Workshop on Machine Learning and Music Y1 - 2013 A1 - Sebastian Böck A1 - Schlüter, Jan A1 - Widmer, Gerhard KW - onset detection KW - peak-picking AB -
We present a new neural network based peak-picking algorithm for common onset detection functions. Compared to existing hand-crafted methods it yields a better performance and leads to a much lower number of false negative detections. The performance is evaluated on basis of a huge dataset with over 25k annotated onsets and shows a significant improvement over existing methods in cases of signals with previously unknown levels.
JF - Proceedings of the 6th International Workshop on Machine Learning and Music CY - Prague, Czech Republic ER - TY - CONF T1 - GestureAgents: An Agent-Based Framework for Concurrent Multi-Task Multi-User Interaction T2 - TEI 2013 Y1 - 2013 A1 - Carles F. Julià A1 - Jordà, S. A1 - Nicolas Earnshaw KW - agent- exclusivity KW - Concurrent interaction KW - gesture framework KW - multi-user AB -While the HCI community has been putting a lot of effort on creating physical interfaces for collaboration, studying multi-user interaction dynamics and creating specific applications to support (and test) this kind of phenomena, it has not addressed the problem of having multiple applications sharing the same interactive space. Having an ecology of rich interactive programs sharing the same interfaces poses questions on how to deal with interaction ambiguity in a cross-application way and still allow different programmers the freedom to program rich unconstrained interaction experiences. This paper describes GestureAgents, a framework demonstrating several techniques that can be used to coordinate different applications in order to have concurrent multi-user multi-tasking interaction and still dealing with gesture ambiguity across multiple applications.
JF - TEI 2013 PB - ACM UR - http://www.mtg.upf.edu/system/files/publications/2013%20TEI13%20GestureAgents.pdf ER - TY - CONF T1 - How to Improve the Statistical Power of the 10-fold Cross Validation Scheme in Recommender Systems T2 - Proceedings of the International Workshop on Reproducibility and Replication in Recommender Systems Evaluation Y1 - 2013 A1 - Košir, Andrej A1 - Odić, Ante A1 - Tkalčič, Marko KW - evaluation KW - experimental design KW - folding KW - paired testing KW - recommender systems JF - Proceedings of the International Workshop on Reproducibility and Replication in Recommender Systems Evaluation PB - ACM CY - New York, NY, USA SN - 978-1-4503-2465-6 UR - http://doi.acm.org/10.1145/2532508.2532510 ER - TY - CONF T1 - Hybrid Retrieval Approaches to Geospatial Music Recommendation T2 - Proceedings of the 35th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) Y1 - 2013 A1 - Markus Schedl A1 - Dominik Schnitzer JF - Proceedings of the 35th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) CY - Dublin, Ireland ER - TY - THES T1 - Informed Source Separation for Multiple Instruments of Similar Timbre T2 - Music Technology Group, Universitat Pompeu Fabra Y1 - 2013 A1 - López, Jakue KW - source Separation KW - Timbre modelling AB -This Master’s thesis focuses on the challenging task of separating the musical audio sources with instruments of similar timbre. We address the case in which external pitch information to assist the separation process is available. This information is provided to the source / filter model, which is embedded in a Non-Negative Matrix Factorization (NMF) framework that processes the audio input spectrogram. Different state of the art literature methods are inspected and extended. As an extension to these, two new separation methods are proposed, the Multi-Excitation and Single Filter Instantaneous Mixture Model and the Multi-Excitation and Multi-Filter Instantaneous Mixture Model. The use of dedicated source and filter decomposition for each instrument is proposed. In addition, we introduce the use of timbre models in the separation process. Timbre models are previously trained on isolated instrument recordings. The methods are compared with the BSS Eval and PEASS evaluation toolkits over an existing dataset. Promising results obtained in the conducted experiments, which shows that this is a path to be further investigated.
JF - Music Technology Group, Universitat Pompeu Fabra VL - Master in Sound and Music Computing UR - http://mtg.upf.edu/system/files/publications/Jakue-Lopez-Master-Thesis-2013.pdf ER - TY - CONF T1 - Innovating the Classical Music Experience in the PHENICX Project: Use Cases and Initial User Feedback T2 - 1st International Workshop on Interactive Content Consumption (WSICC) at EuroITV 2013 Y1 - 2013 A1 - Cynthia C. S. Liem A1 - Ron van der Sterren A1 - Marcel van Tilburg A1 - Álvaro Sarasúa A1 - Juan J. Bosch A1 - Jordi Janer A1 - Mark S. Melenhorst A1 - Emilia Gómez A1 - Alan Hanjalic KW - interactivity KW - multimedia information systems KW - multimodality KW - music information retrieval KW - performing arts KW - social networks KW - user studies AB -The FP7 PHENICX project focuses on creating a new digital classical concert experience, improving the accessibility of classical music concert performances by enhancing and enriching them in novel digital ways, In this paper, we present the project’s foreseen use cases. Subsequently, we summarize initial use case feedback from two different user groups. Despite the early stage of the project, the feedback already gives important insight into real-world considerations to make for interactive music content consumption solutions.
JF - 1st International Workshop on Interactive Content Consumption (WSICC) at EuroITV 2013 CY - Como, Italy ER - TY - CONF T1 - Local Group Delay based Vibrato and Tremolo Suppression for Onset Detection T2 - Proceedings of the 14th International Society for Music Information Retrieval Conference (ISMIR 2013) Y1 - 2013 A1 - Sebastian Böck A1 - Widmer, Gerhard KW - local group delay KW - onset detection KW - tremolo suppression KW - vibrato suppression AB -We present SuperFlux - a new onset detection algorithm with vibrato suppression. It is an enhanced version of the universal spectral flux onset detection algorithm, and reduces the number of false positive detections considerably by tracking spectral trajectories with a maximum filter. Especially for music with heavy use of vibrato (e.g., sung operas or string performances), the number of false positive detections can be reduced by up to 60% without missing any additional events. Algorithm performance was evaluated and compared to state-of-the-art methods on the basis of three different datasets comprising mixed audio material (25,927 onsets), violin recordings (7,677 onsets) and operatic solo voice recordings (1,448 onsets). Due to its causal nature, the algorithm is applicable in both offline and online real-time scenarios.
JF - Proceedings of the 14th International Society for Music Information Retrieval Conference (ISMIR 2013) CY - Curitiba, Brazil ER - TY - CONF T1 - Location-aware Music Recommendation Using Auto-Tagging and Hybrid Matching T2 - Proceedings of the 7th ACM Conference on Recommender Systems (RecSys 2013) Y1 - 2013 A1 - Marius Kaminskas A1 - Francesco Ricci A1 - Markus Schedl JF - Proceedings of the 7th ACM Conference on Recommender Systems (RecSys 2013) CY - Hong Kong, China ER - TY - Generic T1 - Looking Beyond Sound: Unsupervised Analysis of Musician Videos T2 - 14th International Workshop on Image and Audio Analysis for Multimedia Interactive services (WIA2MIS) Y1 - 2013 A1 - Cynthia C. S. Liem A1 - Alessio Bazzica A1 - Alan Hanjalic AB -Many recent approaches to musical source separation rely on model-based inference methods that take into account the signal’s harmonic structure. To address the particular case of low-latency bass separation, we propose a method that combines harmonic decomposition using a Tikhonov regularization-based algorithm, with the peak contrast analysis of the pitch likelihood function. Our experiment compares the separation performance of this method to a naive low-pass filter, a state-of-the-art NMF-based method and a near-optimal binary mask. The proposed low-latency method achieves results similar to the NMF-based high-latency approach at a lower computational cost. Therefore the method is valid for real-time implementations.
JF - International Conference on Digital Audio Effects Conference (DAFx-13) CY - Maynooth, Ireland UR - http://dafx13.nuim.ie/papers/11.dafx2013_submission_13.pdf ER - TY - CONF T1 - Maximum Filter Vibrato Suppression for Onset Detection T2 - Proceedings of the 16th International Conference on Digital Audio Effects (DAFx-13) Y1 - 2013 A1 - Sebastian Böck A1 - Widmer, Gerhard KW - maximum filter KW - onset detection KW - vibrato suppression AB -
We present SuperFlux - a new onset detection algorithm with vibrato suppression. It is an enhanced version of the universal spectral flux onset detection algorithm, and reduces the number of false positive detections considerably by tracking spectral trajectories with a maximum filter. Especially for music with heavy use of vibrato (e.g., sung operas or string performances), the number of false positive detections can be reduced by up to 60% without missing any additional events. Algorithm performance was evaluated and compared to state-of-the-art methods on the basis of three different datasets comprising mixed audio material (25,927 onsets), violin recordings (7,677 onsets) and operatic solo voice recordings (1,448 onsets). Due to its causal nature, the algorithm is applicable in both offline and online real-time scenarios.
JF - Proceedings of the 16th International Conference on Digital Audio Effects (DAFx-13) CY - Maynooth, Ireland ER - TY - CONF T1 - The Million Musical Tweets Dataset: What Can We Learn From Microblogs T2 - Proceedings of the 14th International Society for Music Information Retrieval Conference (ISMIR 2013) Y1 - 2013 A1 - David Hauger A1 - Markus Schedl A1 - Andrej Košir A1 - Marko Tkalčič JF - Proceedings of the 14th International Society for Music Information Retrieval Conference (ISMIR 2013) CY - Curitiba, Brazil ER - TY - THES T1 - Modelling tonal context dynamics by temporal multi-scale analysis Y1 - 2013 A1 - Martorell, Agustín AB -Modern digital multimedia and internet technology have radically changed the ways people find entertainment and discover new interests online, seemingly without any phys- ical or social barriers. Such new access paradigms are in sharp contrast with the traditional means of entertainment. An illustrative example of this is live music concert perfor- mances that are largely being attended by dedicated audi- ences only.
This papers introduces the PHENICX project, which aims at enriching traditional concert experiences by using state- of-the-art multimedia and internet technologies. The project focuses on classical music and its main goal is twofold: (a) to make live concerts appealing to potential new au- dience and (b) to maximize the quality of concert experi- ence for everyone. Concerts will then become multimodal, multi-perspective and multilayer digital artifacts that can be easily explored, customized, personalized, (re)enjoyed and shared among the users. The paper presents the main scientific objectives on the project, provides a state of the art review on related research and presents the main chal- lenges to be addressed.
Rhythmic patterns are an important structural element in music. This paper investigates the use of rhythmic pattern modeling to infer metrical structure in musical audio recordings. We present a Hidden Markov Model (HMM) based system that simultaneously extracts beats, downbeats, tempo, meter, and rhythmic patterns. Our model builds upon the basic structure proposed by Whiteley et. al, which we further modified by introducing a new observation model: rhythmic patterns are learned directly from data, which makes the model adaptable to the rhythmical structure of any kind of music. For learning rhythmic patterns and evaluating beat and downbeat tracking, 697 ballroom dance pieces were annotated with beat and measure information. The results showed that explicitly modeling rhythmic patterns of dance styles drastically reduces octave errors (detection of half or double tempo) and substantially improves downbeat tracking.
JF - Proceedings of the 14th International Society for Music Information Retrieval Conference (ISMIR 2013) ER - TY - CONF T1 - Study of regularizations and constraints in NMF-based drums monaural separation T2 - International Conference on Digital Audio Effects Conference (DAFx-13) Y1 - 2013 A1 - Marxer, R. A1 - Janer, J. KW - drums KW - NMF KW - source Separation AB -Drums modelling is of special interest in musical source separation because of its widespread presence in western popular music. Current research has often focused on drums separation without specifically modelling the other sources present in the signal. This paper presents an extensive study of the use of regularizations and constraints to drive the factorization towards the separation between percussive and non-percussive music accompaniment. The proposed regularizations control the frequency smoothness of the basis components and the temporal sparseness of the gains. We also evaluated the use of temporal constraints on the gains to perform the separation, using both ground truth manual annotations (made publicly available) and automatically extracted transients. Objective evaluation of the results shows that, while optimal regularizations are highly dependent on the signal, drum event position contains enough information to achieve a high quality separation.
JF - International Conference on Digital Audio Effects Conference (DAFx-13) UR - http://dafx13.nuim.ie/papers/16.dafx2013_submission_16.pdf ER - TY - CONF T1 - Tracking Rests and Tempo Changes: Improved Score Following with Particle Filters T2 - Proceedings of the International Computer Music Conference (ICMC) Y1 - 2013 A1 - Korzeniowski, Filip A1 - Krebs, Florian A1 - Andreas Arzt A1 - Widmer, Gerhard AB -In this paper we present a score following system based on a Dynamic Bayesian Network, using particle filtering as inference method. The proposed model sets itself apart from existing approaches by including two new extensions: A multi-level tempo model to improve alignment quality of performances with challenging tempo changes, and an extension to reflect different expressive characteristics of notated rests. Both extensions are evaluated against a dataset of classical piano music. As the results show, the extensions improve both the accuracy and the robustness of the algorithm.
JF - Proceedings of the International Computer Music Conference (ICMC) CY - Perth, Australia ER -