Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 36
Encontrada(s) 1 página(s)

Repositorio Digital de la UPF
Publicación Artículo científico (JournalArticle)

Drum rhythm spaces: from polyphonic similarity to generative maps

  • Gómez-Marín, Daniel
  • Jordà Puig, Sergi
  • Herrera Boyer, Perfecto, 1964-
This paper reports on the design and evaluation of drum rhythm spaces as interactive bi-dimensional maps used for the visualisation, retrieval and generation of drum patterns. We carry out two experiments exploring human processing of polyphonic drum patterns concluding with a list of descriptors that significantly influence similarity sensations. These features are used to build spaces based on drum pattern collections, where patterns are organised by similarity, modelled according to human perception. A drum-interpolation algorithm is introduced (and evaluated) to enhance rhythm space functionality by means of patterns that bound it, converting a discrete space to a continuous generative one., This research has been partially supported by the EU funded GiantSteps project (http://www.giantsteps-project.eu) (FP7-ICT-2013-10 Grant agreement nr 610591).
Repositorio Digital de la UPF
Publicación Contribución de congreso (ConferenceOutput)

The House Harmonic Filler: interactive exploration of chord sequences by means of an intuitive representation

  • Faraldo Pérez, Ángel
  • Herrera Boyer, Perfecto, 1964-
Comunicació presentada a: Third International Conference on Technologies for Music Notation and Representation (TENOR) celebrat el 25 i 26 de maig de 2017 a A Coruña, Espanya., In this paper we present an interactive two-dimensional representation of musical chord progressions, integrated into a computer program that generates house music harmonic loops in MIDI format, based on a user’s input. Our aim is to encapsulate relevant tonal information and display it in ways that are easy to understand for novices and untrained musicians, facilitating the creative exploration of musical ideas. We briefly reference previous work on tonal visualisation and interaction, and introduce some measures of tonal properties from the literature. We then present our system and describe the two-dimensional harmonic map, before discussing its outcomes and shortcomings, pointing at future lines of research in the conclusions., This research has been partially supported by the EUfunded GiantSteps project (FP7-ICT-2013-10 grant agreement number 610591).
Repositorio Digital de la UPF
Publicación Contribución de congreso (ConferenceOutput)

Drumming with style: from user needs to a working prototype

  • Jordà Puig, Sergi
  • Gómez Marín, Daniel
  • Faraldo Pérez, Ángel
  • Herrera Boyer, Perfecto, 1964-
Comunicació presentada a la NIME 2016, International Conference on New Interfaces for Musical Expression, celebrada els dies 11 a 15 de juliol de 2016 a Brisbane, Austràlia., This paper documents and discusses the process of developing a generative drumming agent built from the results of an extensive survey carried out with electronic music producers. Following the techniques of user-centered interaction design, an international group of beat producers was reviewed on the possibility of using AI algorithms to help them in the beat production work-flow. The results of these tests were used as design requirements for constructing a system that would indeed perform some tasks alongside the producer. The first results of this working prototype, a stylistic drum generator that creates new rhythmic patterns after being trained with a collection of drum tracks, are presented with a description of the system. Further stages of development and potential algorithms are also discussed., This research has been partially supported by the EU funded GiantSteps project (FP7-ICT-2013-10 Grant agreement nr 610591).
Repositorio Digital de la UPF
Publicación Contribución de congreso (ConferenceOutput)

k-Best hidden Markov model decoding for unit selection in concatenative sound synthesis

  • Nuanáin, Cárthach Ó
  • Jordà Puig, Sergi
  • Herrera Boyer, Perfecto, 1964-
Comunicació presentada a: The 13th International Symposium on Computer Music Multidisciplinary Research CMMR 201, celebrat del 25 al 28 de setembre de 2017 a Matosinhos, Portugal., Concatenative synthesis is a sample-based approach to sound creation used frequently in speech synthesis and, increasingly, in musical contexts. Unit selection, a key component, is the process by which sounds are chosen from the corpus of samples. With their ability to match target units as well as preserve continuity, Hidden Markov Models are often chosen for this task, but one common criticism is its singular path output which is considered too restrictive when variations are desired. In this article, we propose considering the problem in terms of k-Best path solving for generating alternative lists of candidate solutions and summarise our implementations along with some practical examples., This research has been partially supported by the EU-funded GiantSteps project (FP7-ICT-2013-10 Grant agreement nr 610591).
Repositorio Digital de la UPF
Publicación Artículo científico (JournalArticle)

An intelligent interface for drum pattern variation and comparative evaluation of algorithms

  • Vogl, Richard
  • Leimeister, Matthias
  • Nuanáin, Cárthach Ó
  • Hlatky, Michael
  • Jordà Puig, Sergi
  • Knees, Peter
Drum tracks of electronic dance music pieces are a central and style-defining element. Yet,creating them can be a cumbersome task, mostly due to lack of appropriate tools and inputdevices. In this work we use a UI prototype that aims at supporting musicians to compose therhythmic patterns for drum tracks, to compare different algorithms for drum pattern variation.Starting with a basic pattern (seed pattern), which is provided by the user, a list of variationswith varying degrees of similarity to the seed pattern is generated. The variations are createdusing one of the three algorithms compared: (i) a similarity-based lookup method using arhythm pattern database, (ii) a generative approach based on a stochastic neural network, and(iii) a genetic algorithm using similarity measures as a target function. The interface visualizesthe patterns and provides an intuitive way to browse through them. User test sessions withexperts in electronic music production were conducted to evaluate aspects of the prototype andalgorithms. Additionally a web-based survey was performed to assess perceptual properties ofthe variations in comparison to baseline patterns created by a human expert. The web surveyshows that the algorithms produce musical and interesting variations and that the differentalgorithms have their strengths in different areas. These findings are further supported by theresults of the expert interviews., This work is supported by the European Union’s sev-enth Framework Programme FP7 / 2007-2013 for research,technological development, and demonstration under grantagreement no. 610591 (GiantSteps).
Repositorio Digital de la UPF
Publicación Contribución de congreso (ConferenceOutput)

Two data sets for tempo estimation and key detection in electronic dance music annotated from user corrections

  • Knees, Peter
  • Faraldo Pérez, Ángel
  • Herrera Boyer, Perfecto, 1964-
  • Vogl, Richard
  • Böck, Sebastian
  • Hörschläger, Florian
  • Le Goff, Mickael
Comunicació presentada a: the 16th International Society for Music Information Retrieval Conference (ISMIR), celebrat del 26 al 30 d'octubre de 2015 a Màlaga., We present two new data sets for automatic evaluation of tempo estimation and key detection algorithms. In contrast to existing collections, both released data sets focus on electronic dance music (EDM). The data sets have been automatically created from user feedback and annotations extracted from web sources. More precisely, we utilize user corrections submitted to an online forum to report wrong tempo and key annotations on the Beatport website. Beatport is a digital record store targeted at DJs and focusing on EDM genres. For all annotated tracks in the data sets, samples of at least one-minute-length can be freely downloaded. For key detection, further ground truth is extracted from expert annotations manually assigned to Beatport tracks for benchmarking purposes. The set for tempo estimation comprises 664 tracks and the set for key detection 604 tracks. We detail the creation process of both data sets and perform extensive benchmarks using state-of-theart algorithms from both academic research and commercial products., This work is supported by the European Union Seventh Framework Programme FP7 / 2007-2013 through the GiantSteps project (grant agreement no. 610591).
Repositorio Digital de la UPF
Publicación Contribución de congreso (ConferenceOutput)

Target-based rhythmic pattern generation and variation with genetic algorithms

  • Nuanáin, Cárthach Ó
  • Herrera Boyer, Perfecto, 1964-
  • Jordà Puig, Sergi
Comunicació presentada a: 12th International Conference on Sound and Music Computing (SMC-15) celebrada del 30 de juliol a l'1 d'agost de 2015 a Maynooth, Ireland., Composing drum patterns and musically developing them through repetition and variation is a typical task in electronic music production. We propose a system that, given an input pattern, automatically creates related patterns using a genetic algorithm. Two distance measures (the Hamming distance and directed-swap distance) that relate to rhythmic similarity are shown to derive usable fitness functions for the algorithm. A software instrument in the Max for Live environment presents how this can be used in real musical applications. Finally, a user survey was carried out to examine and compare the effectiveness of the fitness metrics in determining rhythmic similarity as well as the usefulness of the instrument for musical creation., This research has been partially supported by the EU-funded GiantSteps project (FP7-ICT-2013-10 Grant agreement nr 610591).
Repositorio Digital de la UPF
Publicación Contribución de congreso (ConferenceOutput)

What is the effect of audio quality on the robustness of MFCCs and chroma features?

  • Urbano, Julián
  • Bogdanov, Dmitry
  • Herrera Boyer, Perfecto, 1964-
  • Gómez Gutiérrez, Emilia, 1975-
  • Serra, Xavier
Music Information Retrieval is largely based on descriptors computed from audio signals, and in many practical applications they are to be computed on music corpora containing audio files encoded in a variety of lossy formats. Such encodings distort the original signal and therefore may affect the computation of descriptors. This raises the question of the robustness of these descriptors across various audio encodings. We examine this assumption for the case of MFCCs and chroma features. In particular, we analyze their robustness to sampling rate, codec, bitrate, frame size and music genre. Using two different audio analysis tools over a diverse collection of music tracks, we compute several statistics to quantify the robustness of the resulting descriptors, and then estimate the practical effects for a sample task like genre classification., This work is partially supported by an A4U postdoctoral grant and projects SIGMUS (TIN2012-36650), Comp- Music (ERC 267583), PHENICX (ICT-2011.8.2) and GiantSteps (ICT-2013-10).
Repositorio Digital de la UPF
Publicación Contribución de congreso (ConferenceOutput)

PAD and SAD: Two awareness-weighted rhythmic similarity distances

  • Gómez Marín, Daniel
  • Jordà Puig, Sergi
  • Herrera Boyer, Perfecto, 1964-
Comunicació presentada a la 16th International Society for Music Information Retrieval Conference (ISMIR 2015), celebrada els dies 26 a 30 d'octubre de 2015 a Màlaga, Espanya., Measuring rhythm similarity is relevant for the analysis and generation of music. Existing similarity metrics tend to consider our perception of rhythms as being in time without discriminating the importance of some regions over others. In a previously reported experiment we observed that measures of similarity may differ given the presence or absence of a pulse inducing sound and the importance of those measures is not constant along the pattern. These results are now reinterpreted by refining the previously proposed metrics. We consider that the perceptual contribution of each beat to the measured similarity is non-homogeneous but might indeed depend on the temporal positions of the beat along the bar. We show that with these improvements, the correlation between the previously evaluated experimental similarity and predictions based on our metrics increases substantially. We conclude by discussing a possible new methodology for evaluating rhythmic similarity between audio loops., This research has been partially supported by the EU funded GiantSteps project (FP7-ICT- 2013-10 Grant agreement nr 610591).
Repositorio Digital de la UPF
Publicación Contribución de congreso (ConferenceOutput)

An evaluation framework and case study for rhythmic concatenative synthesis

  • Ó Nuanáin, Cárthach
  • Herrera Boyer, Perfecto, 1964-
  • Jordà Puig, Sergi
Comunicació presentada a la 17th International Society for Music Information Retrieval Conference (ISMIR 2016), celebrada els dies 7 a 11 d'agost de 2016 a Nova York, EUA., In this paper we present and report on a methodology for evaluating a creative MIR-based application of concatenative synthesis. After reviewing many existing applications of concatenative synthesis we have developed an application that specifically addresses loop-based rhythmic pattern generation. We describe how such a system could be evaluated with respect to its its objective retrieval performance and subjective responses of humans in a listener survey. Applying this evaluation strategy produced positive findings to help verify and validate the objectives of our system. We discuss the results of the evaluation and draw conclusions by contrasting the objective analysis with the subjective impressions of the users., This research has been partially supported by the EU-funded GiantSteps project (FP7-ICT-2013-10 Grant agreement nr 610591).
Repositorio Digital de la UPF
Publicación Contribución de congreso (ConferenceOutput)

An interactive software instrument for real-time rhythmic concatenative synthesis

  • Ó Nuanáin, Cárthach
  • Jordà Puig, Sergi
  • Herrera Boyer, Perfecto, 1964-
Comunicació presentada a la NIME 2016, International Conference on New Interfaces for Musical Expression, celebrada els dies 11 a 15 de juliol de 2016 a Brisbane, Austràlia., In this paper we describe an approach for generating and visualising new rhythmic patterns from existing audio in real-time using concatenative synthesis. We introduce a graph-based model enabling novel visualisation and manipulation of new patterns that mimics the rhythmic and timbral character of an existing target seed pattern using a separate database of palette sounds. Our approach is described, reporting on those features that may be useful in describing units of sound related to rhythm and how they might then be projected into two-dimensional space for visualisation using reduction techniques and clustering. We conclude the paper with our qualitative appraisal of using the interface and outline scope for future work., This research has been partially supported by the EU-funded GiantSteps project (FP7-ICT-2013-10 Grant agreement nr 610591).
Repositorio Digital de la UPF
Publicación Contribución de congreso (ConferenceOutput)

Key estimation in electronic dance music

  • Faraldo Pérez, Ángel
  • Gómez Gutiérrez, Emilia, 1975-
  • Jordà Puig, Sergi
  • Herrera Boyer, Perfecto, 1964-
Comunicació presentada a la 38th European Conference on IR Research (ECIR 2016), celebrada els dies 20 a 23 de març de 2016 a Pàdua, Itàlia., In this paper we study key estimation in electronic dance music, an umbrella term referring to a variety of electronic music subgenres intended for dancing at nightclubs and raves. We start by defining notions of tonality and key before outlining the basic architecture of a template-based key estimation method. Then, we report on the tonal characteristics of electronic dance music, in order to infer possible modifications of the method described. We create new key profiles combining these observations with corpus analysis, and add two pre-processing stages to the basic algorithm. We conclude by comparing our profiles to existing ones, and testing our modifications on independent datasets of pop and electronic dance music, observing interesting improvements in the performance or our algorithms, and suggesting paths for future research., This research has been partially supported by the EU-funded GiantSteps project (FP7-ICT-2013-10. Grant agreement number 610591).
Repositorio Digital de la UPF
Publicación Contribución de congreso (ConferenceOutput)

Drum rhythm spaces: from global models to style-specific maps

  • Gómez Marín, Daniel
  • Jordà Puig, Sergi
  • Herrera Boyer, Perfecto, 1964-
Comunicació presentada a: The 13th International Symposium on Computer Music Multidisciplinary Research CMMR 201, celebrat del 25 al 28 de setembre de 2017 a Matosinhos, Portugal., This paper presents two experiments carried out to find rhythm descriptors that allow the organization of drum patterns in spaces resembling subjects similarity sensations. We revisit rhythm spaces published by Alf Gabrielsson in 1973, based on subject similarity ratings of drum rhythms from an early drum machine, and construct a new rhythm space based on similarity judgments using contemporary electronic dance music (EDM) patterns. We observe how a specific set of descriptors can be used to reconstruct both Gabrielsson’s and the new EDM space, suggesting the descriptors capture drum similarity sensations in very different contexts. The set of descriptors and the methods employed are explained with detail and the possibility of having method for organizing rhythm patterns automatically is discussed., This research has been partially supported by the EU funded GiantSteps project (http://www.giantsteps-project.eu) (FP7-ICT-2013-10 Grant agreement nr 610591).
Repositorio Digital de la UPF
Publicación Contribución de congreso (ConferenceOutput)

Towards user-tailored creative applications of concatenative synthesis in electronic dance music

  • Ó Nuanáin, Cárthach
  • Jordà Puig, Sergi
  • Herrera Boyer, Perfecto, 1964-
Comunicació presentada al 4th International Workshop on Musical Metacreation (MUME 2016), dins de la Seventh International Conference on Computational Creativity (ICCC 2016), celebrada el 27 de juny de 2016 a París, França., The ecosystem of concatenative synthesis systems is large, diverse and oftentimes esoteric. In this article, we examine many of its key works, attempting to summarise, compare and categorise their characteristic traits. We observe that many existing systems have not taken into account any user other than the designer of the system. Subsequently we position our own implementation in this ecosystem as geared specifically with electronic dance music producers in mind. Through intensive discussion with producers and commercial music software practitioners we summarise their reactions, responses and impressions to the usability and musicality of this approach to music creation. We report on active and future work based on the outcomes of these discussions., This research has been partially supported by the EU-funded GiantSteps project (FP7-ICT-2013-10 Grant agreement nr 610591).
Repositorio Digital de la UPF
Publicación Contribución de congreso (ConferenceOutput)

Giantsteps-progress towards developing intelligent and collaborative interfaces for music production and performance

  • Knees, Peter
  • Andersen, Kristina
  • Jordà Puig, Sergi
  • Hlatky, Michael
  • Geiger, Günter
  • Gaebele, Wulf
  • Kaurson, Roman
We present the GiantSteps project, an EU-funded project/ninvolving institutions from academia, practitioners, and industrial/npartners with the goal of developing new concepts for/nintelligent and collaborative interfaces for music production/nand performance. At the core of the project is an iterative,/nuser-centric research approach to music information retrieval/n(MIR) and human computer interaction (HCI) that is designed/nto allow us to accomplish three main targets, namely (1) the/ndevelopment of intelligent musical expert agents to support/nand inspire music makers, (2) more intuitive and collaborative/ninterfaces, and (3) low-complexity methods addressing lowcost/ndevices to enable affordable and accessible production/ntools and apps. In this paper, we report on the main findings/nand achievements of the project’s first 18 months., This work is supported by the European Union Seventh/nFramework Programme FP7 / 2007-2013 through the GiantSteps/nproject (grant agreement no. 610591).
Repositorio Digital de la UPF
Publicación Contribución de congreso (ConferenceOutput)

Exploring the spontaneous expression of human finger-tapping

  • Nistal, Javier
  • Herrera Boyer, Perfecto, 1964-
  • Jordà Puig, Sergi
Comunicació presentada a: 2nd Conference on Computer Simulation of Musical Creativity celebrat de l'11 al 13 de setembre de 2017 a Milton Keynes, Regne Unit., We present a study on the behavior of human finger-tapping and the spontaneous expression of rhythm. For the purposes of this study we construe interpret finger-tapping as the casual and rhythmic hitting of objects for the expression of music. Our motivation for this study is to connect spontaneous finger-tapping, human-computer interaction and the automatic arrangement of percussion for music creation. Specifically, here we report on the characterization of spontaneous rhythm creation behavior as a prerequisite to develop rhythm-aware music creation interfaces. First, we collect a dataset by recording spontaneous finger-tapping patterns performed by subjects from different music backgrounds. An online survey gathering information about the recording is then submitted to the volunteers. Analysis of the survey answers and low-level audio features suggest that there are two ways for finger-tapping depending on the music skills of the performer (i.e., "experts" versus "naive tappers"). We explore the former hypothesis by conducting a classification task between onsets from both finger-tapping methods. We achieve a 96% of accuracy in recognizing drumming expertise levels (expert vs. naive) by means of using onset-related acoustic features. Results suggest that people with percussion training are more concerned about timbre aspects and, thus, can take advantage of this quality of sound to provide nuances to each stroke when finger-tapping, as opposed to non-expertise individuals., This research has been partially supported by the EU funded GiantSteps project (FP7-ICT-2013-10 Grant agreement nr 610591).
Repositorio Digital de la UPF
Publicación Contribución de congreso (ConferenceOutput)

A multi-profile method for key estimation in EDM

  • Faraldo Pérez, Ángel
  • Jordà Puig, Sergi
  • Herrera Boyer, Perfecto, 1964-
Comunicació presentada a: 2017 AES International Conference on Semantic Audio, celebrada del 22 al 24 de juny de 2017 a Erlangen, Alemanya., Key detection in electronic dance music is important for producers and DJ’s who want to mix their tracks harmonically or organise their music collection by tonal content. In this paper, we present an algorithm that improves the performance of an existing method by introducing a system of multiple profiles, addressing difficult minor tracks as well as possibly amodal ones. After the explanation of our method, we use three independent datasets of electronic dance music to evaluate its performance, comparing it to other academic algorithms and commercially available solutions., This research has been partially supported the EUfunded GiantSteps project (FP7-ICT-2013-10 grant agreement number 610591).
Repositorio Digital de la UPF
Publicación Contribución de congreso (ConferenceOutput)

Rhythm spaces

  • Gómez Marín, Daniel
  • Jordà Puig, Sergi
  • Herrera Boyer, Perfecto, 1964-
Comunicació presentada al 4th International Workshop on Musical Metacreation (MUME 2016), dins de la Seventh International Conference on Computational Creativity (ICCC 2016), celebrada el 27 de juny de 2016 a París, França., We present and discuss our view on rhythm spaces, as metaphors to visualize and interact with rhythms. We take advantage on existing research on alternative lowdimensional music spaces, music cognition, music interaction and intelligent music agents, to justify our position. We then discuss the specific steps and decisions necessary for building rhythm spaces and we advance some of their potential uses as rhythm pattern allocation, retrieval and generation., This research has been partially supported by the EU funded GiantSteps project (FP7-ICT-2013-10 Grant agreement nr 610591).
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Exploring the spontaneous expression of human finger-tapping

  • Nistal, Javier
  • Herrera Boyer, Perfecto, 1964-
  • Jordà Puig, Sergi
Comunicació presentada a: 2nd Conference on Computer Simulation of Musical Creativity celebrat de l'11 al 13 de setembre de 2017 a Milton Keynes, Regne Unit., We present a study on the behavior of human finger-tapping and the spontaneous expression of rhythm. For the purposes of this study we construe interpret finger-tapping as the casual and rhythmic hitting of objects for the expression of music. Our motivation for this study is to connect spontaneous finger-tapping, human-computer interaction and the automatic arrangement of percussion for music creation. Specifically, here we report on the characterization of spontaneous rhythm creation behavior as a prerequisite to develop rhythm-aware music creation interfaces. First, we collect a dataset by recording spontaneous finger-tapping patterns performed by subjects from different music backgrounds. An online survey gathering information about the recording is then submitted to the volunteers. Analysis of the survey answers and low-level audio features suggest that there are two ways for finger-tapping depending on the music skills of the performer (i.e., "experts" versus "naive tappers"). We explore the former hypothesis by conducting a classification task between onsets from both finger-tapping methods. We achieve a 96% of accuracy in recognizing drumming expertise levels (expert vs. naive) by means of using onset-related acoustic features. Results suggest that people with percussion training are more concerned about timbre aspects and, thus, can take advantage of this quality of sound to provide nuances to each stroke when finger-tapping, as opposed to non-expertise individuals., This research has been partially supported by the EU funded GiantSteps project (FP7-ICT-2013-10 Grant agreement nr 610591).
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Rhythm spaces

  • Gómez Marín, Daniel
  • Jordà Puig, Sergi
  • Herrera Boyer, Perfecto, 1964-
Comunicació presentada al 4th International Workshop on Musical Metacreation (MUME 2016), dins de la Seventh International Conference on Computational Creativity (ICCC 2016), celebrada el 27 de juny de 2016 a París, França., We present and discuss our view on rhythm spaces, as metaphors to visualize and interact with rhythms. We take advantage on existing research on alternative lowdimensional music spaces, music cognition, music interaction and intelligent music agents, to justify our position. We then discuss the specific steps and decisions necessary for building rhythm spaces and we advance some of their potential uses as rhythm pattern allocation, retrieval and generation., This research has been partially supported by the EU funded GiantSteps project (FP7-ICT-2013-10 Grant agreement nr 610591).
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

An intelligent interface for drum pattern variation and comparative evaluation of algorithms

  • Vogl, Richard
  • Leimeister, Matthias
  • Nuanáin, Cárthach Ó
  • Hlatky, Michael
  • Jordà Puig, Sergi
  • Knees, Peter
Drum tracks of electronic dance music pieces are a central and style-defining element. Yet,creating them can be a cumbersome task, mostly due to lack of appropriate tools and inputdevices. In this work we use a UI prototype that aims at supporting musicians to compose therhythmic patterns for drum tracks, to compare different algorithms for drum pattern variation.Starting with a basic pattern (seed pattern), which is provided by the user, a list of variationswith varying degrees of similarity to the seed pattern is generated. The variations are createdusing one of the three algorithms compared: (i) a similarity-based lookup method using arhythm pattern database, (ii) a generative approach based on a stochastic neural network, and(iii) a genetic algorithm using similarity measures as a target function. The interface visualizesthe patterns and provides an intuitive way to browse through them. User test sessions withexperts in electronic music production were conducted to evaluate aspects of the prototype andalgorithms. Additionally a web-based survey was performed to assess perceptual properties ofthe variations in comparison to baseline patterns created by a human expert. The web surveyshows that the algorithms produce musical and interesting variations and that the differentalgorithms have their strengths in different areas. These findings are further supported by theresults of the expert interviews., This work is supported by the European Union’s sev-enth Framework Programme FP7 / 2007-2013 for research,technological development, and demonstration under grantagreement no. 610591 (GiantSteps).
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Key estimation in electronic dance music

  • Faraldo Pérez, Ángel
  • Gómez Gutiérrez, Emilia, 1975-
  • Jordà Puig, Sergi
  • Herrera Boyer, Perfecto, 1964-
Comunicació presentada a la 38th European Conference on IR Research (ECIR 2016), celebrada els dies 20 a 23 de març de 2016 a Pàdua, Itàlia., In this paper we study key estimation in electronic dance music, an umbrella term referring to a variety of electronic music subgenres intended for dancing at nightclubs and raves. We start by defining notions of tonality and key before outlining the basic architecture of a template-based key estimation method. Then, we report on the tonal characteristics of electronic dance music, in order to infer possible modifications of the method described. We create new key profiles combining these observations with corpus analysis, and add two pre-processing stages to the basic algorithm. We conclude by comparing our profiles to existing ones, and testing our modifications on independent datasets of pop and electronic dance music, observing interesting improvements in the performance or our algorithms, and suggesting paths for future research., This research has been partially supported by the EU-funded GiantSteps project (FP7-ICT-2013-10. Grant agreement number 610591).
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Two data sets for tempo estimation and key detection in electronic dance music annotated from user corrections

  • Knees, Peter
  • Faraldo Pérez, Ángel
  • Herrera Boyer, Perfecto, 1964-
  • Vogl, Richard
  • Böck, Sebastian
  • Hörschläger, Florian
  • Le Goff, Mickael
Comunicació presentada a: the 16th International Society for Music Information Retrieval Conference (ISMIR), celebrat del 26 al 30 d'octubre de 2015 a Màlaga., We present two new data sets for automatic evaluation of tempo estimation and key detection algorithms. In contrast to existing collections, both released data sets focus on electronic dance music (EDM). The data sets have been automatically created from user feedback and annotations extracted from web sources. More precisely, we utilize user corrections submitted to an online forum to report wrong tempo and key annotations on the Beatport website. Beatport is a digital record store targeted at DJs and focusing on EDM genres. For all annotated tracks in the data sets, samples of at least one-minute-length can be freely downloaded. For key detection, further ground truth is extracted from expert annotations manually assigned to Beatport tracks for benchmarking purposes. The set for tempo estimation comprises 664 tracks and the set for key detection 604 tracks. We detail the creation process of both data sets and perform extensive benchmarks using state-of-theart algorithms from both academic research and commercial products., This work is supported by the European Union Seventh Framework Programme FP7 / 2007-2013 through the GiantSteps project (grant agreement no. 610591).
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

An evaluation framework and case study for rhythmic concatenative synthesis

  • Ó Nuanáin, Cárthach
  • Herrera Boyer, Perfecto, 1964-
  • Jordà Puig, Sergi
Comunicació presentada a la 17th International Society for Music Information Retrieval Conference (ISMIR 2016), celebrada els dies 7 a 11 d'agost de 2016 a Nova York, EUA., In this paper we present and report on a methodology for evaluating a creative MIR-based application of concatenative synthesis. After reviewing many existing applications of concatenative synthesis we have developed an application that specifically addresses loop-based rhythmic pattern generation. We describe how such a system could be evaluated with respect to its its objective retrieval performance and subjective responses of humans in a listener survey. Applying this evaluation strategy produced positive findings to help verify and validate the objectives of our system. We discuss the results of the evaluation and draw conclusions by contrasting the objective analysis with the subjective impressions of the users., This research has been partially supported by the EU-funded GiantSteps project (FP7-ICT-2013-10 Grant agreement nr 610591).
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

An interactive software instrument for real-time rhythmic concatenative synthesis

  • Ó Nuanáin, Cárthach
  • Jordà Puig, Sergi
  • Herrera Boyer, Perfecto, 1964-
Comunicació presentada a la NIME 2016, International Conference on New Interfaces for Musical Expression, celebrada els dies 11 a 15 de juliol de 2016 a Brisbane, Austràlia., In this paper we describe an approach for generating and visualising new rhythmic patterns from existing audio in real-time using concatenative synthesis. We introduce a graph-based model enabling novel visualisation and manipulation of new patterns that mimics the rhythmic and timbral character of an existing target seed pattern using a separate database of palette sounds. Our approach is described, reporting on those features that may be useful in describing units of sound related to rhythm and how they might then be projected into two-dimensional space for visualisation using reduction techniques and clustering. We conclude the paper with our qualitative appraisal of using the interface and outline scope for future work., This research has been partially supported by the EU-funded GiantSteps project (FP7-ICT-2013-10 Grant agreement nr 610591).
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

A multi-profile method for key estimation in EDM

  • Faraldo Pérez, Ángel
  • Jordà Puig, Sergi
  • Herrera Boyer, Perfecto, 1964-
Comunicació presentada a: 2017 AES International Conference on Semantic Audio, celebrada del 22 al 24 de juny de 2017 a Erlangen, Alemanya., Key detection in electronic dance music is important for producers and DJ’s who want to mix their tracks harmonically or organise their music collection by tonal content. In this paper, we present an algorithm that improves the performance of an existing method by introducing a system of multiple profiles, addressing difficult minor tracks as well as possibly amodal ones. After the explanation of our method, we use three independent datasets of electronic dance music to evaluate its performance, comparing it to other academic algorithms and commercially available solutions., This research has been partially supported the EUfunded GiantSteps project (FP7-ICT-2013-10 grant agreement number 610591).
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

The House Harmonic Filler: interactive exploration of chord sequences by means of an intuitive representation

  • Faraldo Pérez, Ángel
  • Herrera Boyer, Perfecto, 1964-
Comunicació presentada a: Third International Conference on Technologies for Music Notation and Representation (TENOR) celebrat el 25 i 26 de maig de 2017 a A Coruña, Espanya., In this paper we present an interactive two-dimensional representation of musical chord progressions, integrated into a computer program that generates house music harmonic loops in MIDI format, based on a user’s input. Our aim is to encapsulate relevant tonal information and display it in ways that are easy to understand for novices and untrained musicians, facilitating the creative exploration of musical ideas. We briefly reference previous work on tonal visualisation and interaction, and introduce some measures of tonal properties from the literature. We then present our system and describe the two-dimensional harmonic map, before discussing its outcomes and shortcomings, pointing at future lines of research in the conclusions., This research has been partially supported by the EUfunded GiantSteps project (FP7-ICT-2013-10 grant agreement number 610591).
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Drumming with style: from user needs to a working prototype

  • Jordà Puig, Sergi
  • Gómez Marín, Daniel
  • Faraldo Pérez, Ángel
  • Herrera Boyer, Perfecto, 1964-
Comunicació presentada a la NIME 2016, International Conference on New Interfaces for Musical Expression, celebrada els dies 11 a 15 de juliol de 2016 a Brisbane, Austràlia., This paper documents and discusses the process of developing a generative drumming agent built from the results of an extensive survey carried out with electronic music producers. Following the techniques of user-centered interaction design, an international group of beat producers was reviewed on the possibility of using AI algorithms to help them in the beat production work-flow. The results of these tests were used as design requirements for constructing a system that would indeed perform some tasks alongside the producer. The first results of this working prototype, a stylistic drum generator that creates new rhythmic patterns after being trained with a collection of drum tracks, are presented with a description of the system. Further stages of development and potential algorithms are also discussed., This research has been partially supported by the EU funded GiantSteps project (FP7-ICT-2013-10 Grant agreement nr 610591).
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Target-based rhythmic pattern generation and variation with genetic algorithms

  • Nuanáin, Cárthach Ó
  • Herrera Boyer, Perfecto, 1964-
  • Jordà Puig, Sergi
Comunicació presentada a: 12th International Conference on Sound and Music Computing (SMC-15) celebrada del 30 de juliol a l'1 d'agost de 2015 a Maynooth, Ireland., Composing drum patterns and musically developing them through repetition and variation is a typical task in electronic music production. We propose a system that, given an input pattern, automatically creates related patterns using a genetic algorithm. Two distance measures (the Hamming distance and directed-swap distance) that relate to rhythmic similarity are shown to derive usable fitness functions for the algorithm. A software instrument in the Max for Live environment presents how this can be used in real musical applications. Finally, a user survey was carried out to examine and compare the effectiveness of the fitness metrics in determining rhythmic similarity as well as the usefulness of the instrument for musical creation., This research has been partially supported by the EU-funded GiantSteps project (FP7-ICT-2013-10 Grant agreement nr 610591).
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Giantsteps-progress towards developing intelligent and collaborative interfaces for music production and performance

  • Knees, Peter
  • Andersen, Kristina
  • Jordà Puig, Sergi
  • Hlatky, Michael
  • Geiger, Günter
  • Gaebele, Wulf
  • Kaurson, Roman
We present the GiantSteps project, an EU-funded project/ninvolving institutions from academia, practitioners, and industrial/npartners with the goal of developing new concepts for/nintelligent and collaborative interfaces for music production/nand performance. At the core of the project is an iterative,/nuser-centric research approach to music information retrieval/n(MIR) and human computer interaction (HCI) that is designed/nto allow us to accomplish three main targets, namely (1) the/ndevelopment of intelligent musical expert agents to support/nand inspire music makers, (2) more intuitive and collaborative/ninterfaces, and (3) low-complexity methods addressing lowcost/ndevices to enable affordable and accessible production/ntools and apps. In this paper, we report on the main findings/nand achievements of the project’s first 18 months., This work is supported by the European Union Seventh/nFramework Programme FP7 / 2007-2013 through the GiantSteps/nproject (grant agreement no. 610591).
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

PAD and SAD: Two awareness-weighted rhythmic similarity distances

  • Gómez Marín, Daniel
  • Jordà Puig, Sergi
  • Herrera Boyer, Perfecto, 1964-
Comunicació presentada a la 16th International Society for Music Information Retrieval Conference (ISMIR 2015), celebrada els dies 26 a 30 d'octubre de 2015 a Màlaga, Espanya., Measuring rhythm similarity is relevant for the analysis and generation of music. Existing similarity metrics tend to consider our perception of rhythms as being in time without discriminating the importance of some regions over others. In a previously reported experiment we observed that measures of similarity may differ given the presence or absence of a pulse inducing sound and the importance of those measures is not constant along the pattern. These results are now reinterpreted by refining the previously proposed metrics. We consider that the perceptual contribution of each beat to the measured similarity is non-homogeneous but might indeed depend on the temporal positions of the beat along the bar. We show that with these improvements, the correlation between the previously evaluated experimental similarity and predictions based on our metrics increases substantially. We conclude by discussing a possible new methodology for evaluating rhythmic similarity between audio loops., This research has been partially supported by the EU funded GiantSteps project (FP7-ICT- 2013-10 Grant agreement nr 610591).
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

What is the effect of audio quality on the robustness of MFCCs and chroma features?

  • Urbano, Julián
  • Bogdanov, Dmitry
  • Herrera Boyer, Perfecto, 1964-
  • Gómez Gutiérrez, Emilia, 1975-
  • Serra, Xavier
Music Information Retrieval is largely based on descriptors computed from audio signals, and in many practical applications they are to be computed on music corpora containing audio files encoded in a variety of lossy formats. Such encodings distort the original signal and therefore may affect the computation of descriptors. This raises the question of the robustness of these descriptors across various audio encodings. We examine this assumption for the case of MFCCs and chroma features. In particular, we analyze their robustness to sampling rate, codec, bitrate, frame size and music genre. Using two different audio analysis tools over a diverse collection of music tracks, we compute several statistics to quantify the robustness of the resulting descriptors, and then estimate the practical effects for a sample task like genre classification., This work is partially supported by an A4U postdoctoral grant and projects SIGMUS (TIN2012-36650), Comp- Music (ERC 267583), PHENICX (ICT-2011.8.2) and GiantSteps (ICT-2013-10).
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Drum rhythm spaces: from polyphonic similarity to generative maps

  • Gómez-Marín, Daniel
  • Jordà Puig, Sergi
  • Herrera Boyer, Perfecto, 1964-
This paper reports on the design and evaluation of drum rhythm spaces as interactive bi-dimensional maps used for the visualisation, retrieval and generation of drum patterns. We carry out two experiments exploring human processing of polyphonic drum patterns concluding with a list of descriptors that significantly influence similarity sensations. These features are used to build spaces based on drum pattern collections, where patterns are organised by similarity, modelled according to human perception. A drum-interpolation algorithm is introduced (and evaluated) to enhance rhythm space functionality by means of patterns that bound it, converting a discrete space to a continuous generative one., This research has been partially supported by the EU funded GiantSteps project (http://www.giantsteps-project.eu) (FP7-ICT-2013-10 Grant agreement nr 610591).
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Towards user-tailored creative applications of concatenative synthesis in electronic dance music

  • Ó Nuanáin, Cárthach
  • Jordà Puig, Sergi
  • Herrera Boyer, Perfecto, 1964-
Comunicació presentada al 4th International Workshop on Musical Metacreation (MUME 2016), dins de la Seventh International Conference on Computational Creativity (ICCC 2016), celebrada el 27 de juny de 2016 a París, França., The ecosystem of concatenative synthesis systems is large, diverse and oftentimes esoteric. In this article, we examine many of its key works, attempting to summarise, compare and categorise their characteristic traits. We observe that many existing systems have not taken into account any user other than the designer of the system. Subsequently we position our own implementation in this ecosystem as geared specifically with electronic dance music producers in mind. Through intensive discussion with producers and commercial music software practitioners we summarise their reactions, responses and impressions to the usability and musicality of this approach to music creation. We report on active and future work based on the outcomes of these discussions., This research has been partially supported by the EU-funded GiantSteps project (FP7-ICT-2013-10 Grant agreement nr 610591).
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

k-Best hidden Markov model decoding for unit selection in concatenative sound synthesis

  • Nuanáin, Cárthach Ó
  • Jordà Puig, Sergi
  • Herrera Boyer, Perfecto, 1964-
Comunicació presentada a: The 13th International Symposium on Computer Music Multidisciplinary Research CMMR 201, celebrat del 25 al 28 de setembre de 2017 a Matosinhos, Portugal., Concatenative synthesis is a sample-based approach to sound creation used frequently in speech synthesis and, increasingly, in musical contexts. Unit selection, a key component, is the process by which sounds are chosen from the corpus of samples. With their ability to match target units as well as preserve continuity, Hidden Markov Models are often chosen for this task, but one common criticism is its singular path output which is considered too restrictive when variations are desired. In this article, we propose considering the problem in terms of k-Best path solving for generating alternative lists of candidate solutions and summarise our implementations along with some practical examples., This research has been partially supported by the EU-funded GiantSteps project (FP7-ICT-2013-10 Grant agreement nr 610591).
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Drum rhythm spaces: from global models to style-specific maps

  • Gómez Marín, Daniel
  • Jordà Puig, Sergi
  • Herrera Boyer, Perfecto, 1964-
Comunicació presentada a: The 13th International Symposium on Computer Music Multidisciplinary Research CMMR 201, celebrat del 25 al 28 de setembre de 2017 a Matosinhos, Portugal., This paper presents two experiments carried out to find rhythm descriptors that allow the organization of drum patterns in spaces resembling subjects similarity sensations. We revisit rhythm spaces published by Alf Gabrielsson in 1973, based on subject similarity ratings of drum rhythms from an early drum machine, and construct a new rhythm space based on similarity judgments using contemporary electronic dance music (EDM) patterns. We observe how a specific set of descriptors can be used to reconstruct both Gabrielsson’s and the new EDM space, suggesting the descriptors capture drum similarity sensations in very different contexts. The set of descriptors and the methods employed are explained with detail and the possibility of having method for organizing rhythm patterns automatically is discussed., This research has been partially supported by the EU funded GiantSteps project (http://www.giantsteps-project.eu) (FP7-ICT-2013-10 Grant agreement nr 610591).