Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 10
Encontrada(s) 1 página(s)

Repositorio Digital de la UPF
Publication Contribución de congreso (ConferenceOutput)

Mining melodic patterns in large audio collections of Indian art music

  • Gulati, Sankalp
  • Serrà Julià, Joan
  • Ishwar, Vignesh
  • Serra, Xavier
Comunicació presentada a la 10th International Conference on Signal Image Technology and Internet Based Systems celebrada del 23 al 27 de novembre de 2014 a Marràqueix (Marroc)., Discovery of repeating structures in music is fundamental to its analysis, understanding and interpretation. We present a data-driven approach for the discovery of shorttime melodic patterns in large collections of Indian art music. The approach first discovers melodic patterns within an audio recording and subsequently searches for their repetitions in the entire music collection. We compute similarity between melodic patterns using dynamic time warping (DTW). Furthermore, we investigate four different variants of the DTW cost function for rank refinement of the obtained results. The music collection used in this study comprises 1,764 audio recordings with a total duration of 365 hours. Over 13 trillion DTW distance computations are done for the entire dataset. Due to the computational complexity of the task, different lower bounding and early abandoning techniques are applied during DTW distance computation. An evaluation based on expert feedback on a subset of the dataset shows that the discovered melodic patterns are musically relevant. Several musically interesting relationships are discovered, yielding further scope for establishing novel similarity measures based on melodic patterns. The discovered melodic patterns can further be used in challenging computational tasks such as automatic r¯aga recognition, composition identification and music recommendation., This work is partly supported by the European Research Council under the European Union’s Seventh Framework Program, as part of the CompMusic project (ERC grant agreement 267583). J.S. acknowledges 2009-SGR- 1434 from Generalitat de Catalunya, ICT-2011-8-318770 from the European Commission, JAEDOC069/2010 from CSIC, and European Social Funds.
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Contribución de congreso (ConferenceOutput)

Personalised automated assessments

  • Gutierrez, Patricia
  • Osman, Nardine
  • Sierra, Carles
Consider an evaluator, or an assessor, who needs to assess a large amount of information. For instance, think of a tutor in a massive open online course with thousands of enrolled students, a senior program committee member in a large peer review process who needs to decide what are the final marks of reviewed papers, or a user in an e-commerce scenario where the user needs to build up its opinion about products evaluated by others. When assessing a large number of objects, sometimes it is simply unfeasible to evaluate them all and often one may need to rely on the opinions of others. In this paper we provide a model that uses peer assessments to generate expected assessments and tune them for a particular assessor. Furthermore, we are able to provide a measure of the uncertainty of our computed assessments and a ranking of the objects that should be assessed next in order to decrease the overall uncertainty of the calculated assessments., This work is supported by the CollectiveMind project (funded by the Spanish Ministry of Economy and Competitiveness, under grant number TEC2013-49430-EXP) and the PRAISE project (funded by the European Commission, under grant number 318770)., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Contribución de congreso (ConferenceOutput)

Trust, negotiations and virtual currencies for a sharing economy

  • De Jonge, Dave
  • Sierra, Carles
We propose an application that allows users to request other users for help with every-day tasks. Users can pay each other for these tasks by issuing contracts in which the requester promises to return the favor in the future by performing some task for the other. Such contracts can be seen as an alternative currency, coined by the users themselves. Trust is an essential aspect of this system, as the issuer of a contract may fail to fulfill its commitments. Therefore, the application comes with a social network where users can leave comments about other users. Furthermore, our application includes a market place where users can exchange service contracts between each other, and a negotiation algorithm that can automatically trade these contracts on behalf of the user., Supported by MILESS - Ministerio de economía y competitividad - TIN2013-45039-P, CollectiveMind - Ministerio de Economía y Competitividad, CONVOCATORIA 2013 - EXPLORA, TEC2013-49430-EXP and EU project 318770 PRAISE, Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Contribución de congreso (ConferenceOutput)

SIMPLE: a Language for the Specification of Protocols, Similar to Natural Language

  • De Jonge, Dave
  • Sierra, Carles
Large and open societies of agents require regulation, and therefore many tools have been developed that enable the definition and enforcement of rules on multiagent systems. Unfortunately, most of them are designed to be used by computer scientists and are not suitable for normal users with average computer skills. Since more and more tools nowadays are running as cloud services accessible to anyone (e.g. Massive Open Online Courses and social networks), we feel there is a need for a simple tool that allows ordinary people to create rules and protocols for these kinds of environments. In this paper we present ongoing work on the development of a new programming language for the definition of protocols for multiagent systems, which is so simple that anyone should be able to use it. Although its syntax is strict, it looks very similar to natural language so that protocols written in this language can be understood directly by anyone, without having to learn the language beforehand. Moreover, we have implemented an easy to use editor that helps users writing sentences that obey the syntax rules, and we have implemented an interpreter that can parse such protocols and verify whether they are violated or not, Supported by the Agreement Technologies CONSOLIDER project, contract CSD2007-0022 and INGENIO 2010 and CHIST-ERA project ACE and EU project 318770 PRAISE, Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Contribución de congreso (ConferenceOutput)

Towards a Framework for Socio-Cognitive Technical Systems

  • Noriega, Pablo
  • Padget, Julian
  • Verhagen, Harko
  • D'Inverno, Mark
This paper is an invitation to carry out science and engineering for a class of socio-technical systems where individuals — who may be human or artificial entities — engage in purposeful collective interactions within a shared web-mediated social space. We put forward a characterization of these systems and introduce some conceptual distinctions that may help to plot the work ahead. In particular, we propose a tripartite view (WIT Trinity) that highlights the interplay between the institutional models that prescribe the behaviour of participants, the corresponding implementation of these prescriptions and the actual performance of the system. Building on this tripartite view we explore the problem of developing a conceptual framework for modelling this type of systems and how that framework can be supported by technological artefacts that implement the resulting models. The last section of this position paper outlines a list of challenges that we believe are worth facing. This work draws upon the contributions that the MAS community has made to the understanding and realization of the concepts of coordination, norms and institutions from an organisational perspective. © Springer International Publishing Switzerland 2015., The authors wish to acknowledge the support of SINTELNET (FET Open Coordinated Action FP7-ICT-2009-C Project No. 286370) in the writing of this paper. In addition, d’Inverno acknowledges the support of the FP7 Technology Enhanced Learning Program Project: Practice and Performance Analysis Inspiring Social Education (PRAISE)., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Contribución de congreso (ConferenceOutput)

Estimation of Guitar Fingering and Plucking Controls based on Multimodal Analysis of Motion, Audio and Musical Score

  • Perez-Carrillo, Alfonso
  • Arcos Rosell, Josep Lluís
  • Wanderley, Marcelo
This work presents a method for the extraction of instrumental controls during guitar performances. The method is based on the analysis of multimodal data consisting of a combination of motion capture, audio analysis and musical score. High speed video cameras based on marker identification are used to track the position of finger bones and articulations and audio is recorded with a transducer measuring vibration on the guitar body. The extracted parameters are divided into left hand controls, i.e. fingering (which string and fret is pressed with a left hand finger) and right hand controls, i.e. the plucked string, the plucking finger and the characteristics of the pluck (position, velocity and angles with respect to the string). Controls are estimated based on probability functions of low level features, namely, the plucking instants (i.e. note onsets), the pitch and the distances of the fingers (both hands) to strings and frets. Note onsets are detected via audio analysis, the pitch is extracted from the score and distances are computed from 3D Euclidean Geometry. Results show that by combination of multimodal information, it is possible to estimate such a comprehensive set of control features, with special high performance for the fingering and plucked string estimation. Regarding the plucking finger and the pluck characteristics, their accuracy gets lower but improvements are foreseen including a hand model and the use of high-speed cameras for calibration and evaluation., A. Perez-Carrillo was supported by a Beatriu de Pinos grant 2010 BP-A 00209 by the Catalan Research Agency (AGAUR) and J. Ll. Arcos was supported by ICT -2011-8-318770 and 2009-SGR-1434 projects, Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Contribución de congreso (ConferenceOutput)

Social machines for education driven by feedback agents

  • Yee-King, Matthew
  • D'Inverno, Mark
  • Noriega, Pablo
The aim of this paper is to explain some of the ways in which multi agent system (MAS) theory can be used to describe, design and enhance social machines (also referred to as Socio-Cognitive Systems). We believe there is a really opportunity for the MAS community to engage with emerging theory and practice of designing such systems. Social machines - also referred to as Socio-Cognitive Systems from the MAS community - are terms used to refer to the recent breed of technological systems which allow human and computational agents to socially interact, typically on a large scale and sometimes towards achieving shared goals. Examples include social networking platforms and crowd sourced encyclopaedias. The discussion of social machines and MAS is taken from three perspectives. Firstly, the theoretical notion of an abstract social machine as a socio-cognitive system containing humans and agents is introduced. Secondly, a speci#12;c instance of a social machine which has been designed to enable social music learning supported by agents is described. Thirdly, an agent architecture which is designed for operation within educational social machines is discussed, with particular focus on what we believe is the core currency of these machines: feedback., Much of of this work was undertaken as part of the FP7 project in the Technology Enhanced Learning Program called Practice and Performance Analysis Inspiring Social Education (PRAISE) involving the 1st and 2nd authors. We acknowledge Harry Brenton, Marco Gillies Andreu Grimalt-Reynes, Jonathan James, Edgar Jones, Julian Padget and Harko Harko Verhagen who have helped in discussions. The second author received support from the European Network for Social Intelligence, SINTELNET (FET Open Coordinated Action FP7-ICT-2009-C Project No. 286370) for short term visits to the IIIA to work with the 3rd author., Peer Reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Contribución de congreso (ConferenceOutput)

Charters for Self-Evolving Communities

  • Osman, Nardine
  • Sierra, Carles
  • Schorlemmer, Marco
Self-organisation and self-evolution is evident in physics, chem-istry, biology, and human societies. Despite the existing literature on the topic, we believe self-organisation and self-evolution is still missing in the IT tools we are building and using. Instead of creating numerous rigid systems, we should aim at providing tools for creating self-evolving systems that adapt to the ever evolving community's needs. This pa- per proposes a roadmap for self-evolution by presenting a set of building blocks, which we refer to as community charters. The paper also presents an approach for each of these blocks, helping build the first prototype for self-evolving communities., This work is supported by the PRAISE project (funded by the European Commission under the FP7 STREP grant number 318770), the CBIT project (funded by the Spanish Ministry of Science & Innovation under the grant number TIN2010-16306), and the Agreement Technologies project (funded by CONSOLIDER CSD 2007-0022, INGENIO 2010)., Peer Reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Contribución de congreso (ConferenceOutput)

Towards cover group thumbnailing

  • Grosche, Peter
  • Muller, Meinard
  • Serrà, Joan
In this paper we investigate whether we can extract the commonalities shared by a group of cover songs or versions of the same musical piece. As a main contribution, we introduce the concept of cover group thumbnail, which is the most representative, essential subsequence for an entire group of versions. Opposed to previous approaches, we jointly consider all versions of a given song to compute a single cover group template, which then shows a high degree of robustness against version-specific aspects. To compute such a template, we introduce a modification of a recent audio thumbnailing technique. To evaluate the reliability of our conceptual contribution, we consider the task of templatebased version identification, where we show comparable accuracies to existing systems. Copyright © 2013 ACM., This work was supported by the Cluster of Excellence on Multimodal Computing and Interaction at Saarland University, JAEDOC069/2010, FP7-ICT-2011-8-318770, and 2009-SGR-1434. The International Audio Laboratories Erlangen are a joint institution of the Friedrich-Alexander-Universitat Erlangen-Nurnberg (FAU) and Fraunhofer IIS, Peer Reviewed
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Mining melodic patterns in large audio collections of Indian art music

  • Gulati, Sankalp
  • Serrà Julià, Joan
  • Ishwar, Vignesh
  • Serra, Xavier
Comunicació presentada a la 10th International Conference on Signal Image Technology and Internet Based Systems celebrada del 23 al 27 de novembre de 2014 a Marràqueix (Marroc)., Discovery of repeating structures in music is fundamental to its analysis, understanding and interpretation. We present a data-driven approach for the discovery of shorttime melodic patterns in large collections of Indian art music. The approach first discovers melodic patterns within an audio recording and subsequently searches for their repetitions in the entire music collection. We compute similarity between melodic patterns using dynamic time warping (DTW). Furthermore, we investigate four different variants of the DTW cost function for rank refinement of the obtained results. The music collection used in this study comprises 1,764 audio recordings with a total duration of 365 hours. Over 13 trillion DTW distance computations are done for the entire dataset. Due to the computational complexity of the task, different lower bounding and early abandoning techniques are applied during DTW distance computation. An evaluation based on expert feedback on a subset of the dataset shows that the discovered melodic patterns are musically relevant. Several musically interesting relationships are discovered, yielding further scope for establishing novel similarity measures based on melodic patterns. The discovered melodic patterns can further be used in challenging computational tasks such as automatic r¯aga recognition, composition identification and music recommendation., This work is partly supported by the European Research Council under the European Union’s Seventh Framework Program, as part of the CompMusic project (ERC grant agreement 267583). J.S. acknowledges 2009-SGR- 1434 from Generalitat de Catalunya, ICT-2011-8-318770 from the European Commission, JAEDOC069/2010 from CSIC, and European Social Funds.