Conference Program

ProgramaFinalISMIR2013

Sunday Nov.3 – 14:00-18:00

Registration

fachada-bourbon-curitiba-convention-hotelsit

At Bourbon Curitiba Convention Hotel (number 1 in the map).

  • The registration desk will be open at the Foyer (1st floor).

Sunday Nov.3 – 19:30-22:00

Welcome Reception and Invited Concert

GaribaldiPalace

At Garibaldi Palace (number 7 in the map)

  • Concert with the Carcoarco ensemble. For more details see the Concerts.
  • At the welcome reception you will have the opportunity to taste the “Caipirinha”, a traditional Brazilian welcome drink, beers and hot and cold snacks. Do not miss!

Monday Nov.4 – 8:00-17:00

Registration

The registration desk will be open at the Foyer (1st floor).

Monday Nov.4 – 9:00-12:40

Tutorial 1

Bourbon Auditorium (1st floor)

Why is Brazilian Guitar Interesting?
François Pachet (Sony Computer Science Lab, France) and Giordano Cabral (Daccord Music Software and the MusiGames Studio, Brazil)

Tutorial 2

All Seasons Hall (ground floor)

Music Autotagging
Mohamed Sordo (Universitat Pompeu Fabra, Spain) and Emanuele Coviello (University of California at San Diego, USA)

Monday Nov.4 – 12:40-14:00

Lunch

99 Brasserie Café (1st floor)

Monday Nov.4 – 14:00-17:20

Tutorial 3

Bourbon Auditorium (1st floor)

Deep Learning in MIR – Demystifying the Dark Art
Philippe Hamel (National Institute of Advanced Industrial Science and Technology, Japan), Eric J. Humphrey (New York University, USA) and Erik M. Schmidt (Drexel University, USA)

Tutorial 4

All Seasons Hall (ground floor)

Conditional Random Fields with Application to Music Analysis
Slim Essid (Telecom ParisTech, France)


Tuesday Nov.5 – 8:40-9:00
Opening

Bourbon Auditorium (1st floor)

Tuesday Nov.5 – 9:00-10:20
OS1: Representation Learning

Bourbon Auditorium (1st floor)

Multiscale Approaches To Music Audio Feature Learning
Sander Dieleman and Benjamin Schrauwen
Ghent University, Belgium

Transfer Learning In Mir: Sharing Learned Latent Representations For Music Audio Classification And Similarity
Philippe Hamel, Matthew E. P. Davies, Kazuyoshi Yoshii and Masataka Goto
National Institute of Advanced Industrial Science and Technology, Japan

A Distributed Model For Multiple-Viewpoint Melodic Prediction
Srikanth Cherla, Tillman Weyde, Artur d’Avila Garcez and Marcus Pearce
City University London, UK | Queen Mary University of London, UK

Learning Rhythm And Melody Features With Deep Belief Networks
Erik Schmidt and Youngmoo Kim
Drexel University, USA

Tuesday Nov.5 – 10:20-11:00 

Poster Craze

Bourbon Auditorium (1st floor)

Tuesday Nov.5 – 11:00-12:40 and 16:00-17:20
PS1: Poster Session 1

All Seasons Hall (ground floor)

A Comparative Study Of Indian And Western Music Forms
Parul Agarwal, Harish Karnick and Bhiksha Raj
Indian Institute of Technology, India | Carnegie Mellon University, USA

Swara Histogram Based Structural Analysis And Identification Of Indian Classical Ragas
Pranay Dighe, Harish Karnick and Bhiksha Raj
Carnegie Mellon University, USA

Combining Modeling Of Singing Voice And Background Music For Automatic Separation Of Musical Mixtures
Zafar Rafii, Francois Germain, Dennis Sun and Gautham Mysore
Northwestern University, USA | Stanford University, USA | Adobe Research, USA

On Finding Symbolic Themes Directly From Audio Files Using Dynamic Programming
Antti Laaksonen and Kjell Lemström
University of Helsinki, Finland | Laurea University of Applied Sciences, Finland

Towards Light-Weight, Real-Time-Capable Singing Voice Detection
Bernhard Lehner, Reinhard Sonnleitner and Gerhard Widmer
Johannes Kepler University of Linz, Austria

The Use Of Melodic Scales In Bollywood Music: An Empirical Study
Monojit Choudhury, Ranjita Bhagwan and Kalika Bali
Microsoft Research Lab India

Bilevel Sparse Models for Polyphonic Music Transcription
Tal Ben Yakar, Pablo Sprechmann, Roee Litman, Alex Bronstein and Guillermo Sapiro
Tel Aviv University, Israel | Duke University, USA

JProductionCritic: An Educational Tool for Detecting Technical Errors in Audio Mixes
Cory McKay
Marianopolis College and CIRMMT, Canada

Combining Timbric and Rhythmic Features for Semantic Music Tagging
Nicola Orio and Roberto Piva
University of Padua, Italy

The Audio Degradation Toolbox and Its Application to Robustness Evaluation
Matthias Mauch and Sebastian Ewert
Queen Mary University of London, UK

Do Online Social Tags Predict Perceived or Induced Emotional Responses to Music?
Yading Song, Simon Dixon, Marcus Pearce and Andrea Halpern
Queen Mary University of London, UK | Bucknell University, USA

A Video Compression-Based Approach to Measure Music Structural Similarity
Diego Silva, Hélène Papadopoulos, Gustavo Batista and Daniel Ellis
Universidade de São Paulo, Brazil | CNRS, France | Columbia University, USA

Dunya: A System to Browse Audio Music Collections Exploiting Cultural Context
Alastair Porter, Mohamed Sordo and Xavier Serra
Universitat Pompeu Fabra, Spain

An Analysis of Chorus Features in Popular Song
Jan Van Balen, John Ashley Burgoyne, Frans Wiering and Remco Veltkamp
Utrecht University, The Netherlands | Universiteit van Amsterdam, The Netherlands

Visual Humdrum-Library for PWGL
Mika Kuuskankare and Craig Sapp
Sibelius Academy, Finland | Stanford University, USA

Source Separation of Polyphonic Music with Interactive User-Feedback on a Piano Roll Display
Nicholas J. Bryan, Gautham J. Mysore and Ge Wang
Stanford University, USA | Adobe Research, USA

Optical Measure Recognition in Common Music Notation
Gabriel Vigliensoni, Gregory Burlet and Ichiro Fujinaga
McGill University, Canada

Musicbrainz for The World: The Chilean Experience
Gabriel Vigliensoni, John Ashley Burgoyne and Ichiro Fujinaga
McGill University, Canada | University of Amsterdam, The Netherlands

Influences of ISMIR and MIREX Research on Technology Patents
Sally Jo Cunningham and Jin Ha Lee
University of Waikato, New Zeland | University of Washington, USA

Toward Understanding Expressive Percussion Through Content Based Analysis
Matthew Prockup, Erik Schmidt, Jeffrey Scott and Youngmoo Kim
Drexel University, USA

Data Driven and Discriminative Projections for Large-Scale Cover Song Identification
Eric J. Humphrey, Oriol Nieto and Juan P. Bello
New York University, USA

Simultaneous Unsupervised Learning of Flamenco Metrical Structure, Hypermetrical Structure, and Multipart Structural Relations
Dekai Wu
HKUST, Hong Kong

Tuesday Nov.5 – 12:40-14:00
Lunch

99 Brasserie Café (1st floor)

Tuesday Nov. 5 – 14:00-15:00
Invited Talk

Bourbon Auditorium (1st floor)

Style Manipulation as a Creative Device
François Pachet, Sony Computer Science Lab, France

Tuesday Nov. 5 – 15:00-16:00
OS2: Musical Cultures

Bourbon Auditorium (1st floor)

A Corpus-Based Study on Ragtime Syncopation
Anja Volk and W. Bas de Haas
Utrecht University, The Netherlands

A Computational Comparison of Theory And Practice of Scale Intonation in Byzantine Chant
Maria Panteli and Hendrik Purwins
University of Cyprus, Cyprus | Berlin Institute of Technology, Germany | Aalborg University Copenhagen, Denmark

Score Informed Tonic Identification for Makam Music of Turkey
Sertan Şentürk, Sankalp Gulati and Xavier Serra
Universitat Pompeu Fabra, Spain

Tuesday Nov.5 – 16:00-17:20
PS1: Poster Session 1 Cont.

All Seasons Hall (ground floor)

Tuesday Nov.5 – 18:00-20:20
Concert II: Selected Works

Bourbon Auditorium (1st floor)

Wednesday Nov.6 – 9:00-10:20
OS3: Text Processing

Bourbon Auditorium (1st floor)

Placing Music Artists and Songs in Time Using Editorial Metadata and Web Mining Techniques
Dimitrios Bountouridis, Remco C. Veltkamp and Jan Van Balen
Utrecht University, The Netherlands

The Million Musical Tweet Dataset – What We Can Learn From Microblogs
David Hauger, Markus Schedl, Andrej Košir and Marko Tkalčič
Johannes Kepler University, Austria | University of Ljubljana, Slovenia

Verifying Music Tag Annotation Via Association Analysis
Tom Arjannikov, Chris Sanden and John Z. Zhang
University of Lethbridge, Canada

The Role of Audio and Tags in Music Mood Prediction: A Study Using Semantic Layer Projection
Pasi Saari, Tuomas Eerola, György Fazekas, Mathieu Barthet, Olivier Lartillot and Mark Sandler
University of Jyvaskyla, Finland | Queen Mary University of London, UK

Wednesday Nov.6 – 10:20-11:00
Poster Craze

Bourbon Auditorium (1st floor)

Wednesday Nov.6 – 11:00-12:40 and 15:00-16:20
PS2: Poster Session 2

All Seasons Hall (ground floor)

Converting Path Structures Into Block Structures Using Eigenvalue Decompositions of Self-Similarity Matrices
Harald Grohganz, Michael Clausen, Nanzhu Jiang and Meinard Mueller
Bonn University, Germany | International Audio Laboratories Erlangen, Germany

The Audio Effects Ontology
Thomas Wilmering, György Fazekas and Mark B. Sandler
Queen Mary University of London, UK

Exploration of Music Emotion Recognition Based on MIDI
Yi Lin, Xiaoou Chen and Deshun Yang
Peking University, China

Rhythmic Pattern Modeling for Beat and Downbeat Tracking in Musical Audio
Florian Krebs, Sebastian Böck and Gerhard Widmer
Johannes Kepler University, Austria

Large-Scale Cover Song Identification Using Chord Profiles
Maksim Khadkevich and Maurizio Omologo
Fondazione Bruno Kessler-irst, Italy

Automatically Identifying Vocal Expressions for Music Transcription
Sai Sumanth Miryala, Kalika Bali, Ranjita Bhagwan and Monojit Choudhury
Microsoft Research India

Hooked: A Game For Discovering What Makes Music Catchy
John Ashley Burgoyne, Dimitrios Bountouridis, Jan Van Balen and Henkjan Honing
Universiteit van Amsterdam, The Netherlands | Universiteit Utrecht, The Netherlands

Hierarchical Classification of Carnatic Music Forms
Ranjani H. G. and T. V. Sreenivas
Indian Institute of Science, India

A Simple Fusion Method of State And Sequence Segmentation for Music Structure Discovery
Florian Kaiser and Geoffroy Peeters
STMS IRCAM-CNRS-UPMC, France

Evaluating The Quality of Generated Playlists Based on Hand-Crafted Samples
Geoffray Bonnin and Dietmar Jannach
TU Dortmund, Germany

Explicit Duration Hidden Markov Models for Multiple-Instrument Polyphonic Music Transcription
Emmanouil Benetos and Tillman Weyde
City University London, UK

A Comprehensive Online Database of Machine-Readable Lead-Sheets for Jazz Standards
Francois Pachet, Jeff Suzda and Dani Martinez
Sony CSL, France

MeUse: Recommending Internet Radio Stations
Maurice Grant, Adeesha Ekanayake and Douglas Turnbull
Ithaca College, USA

Improved Audio Classification Using a Novel Non-Linear Dimensionality Reduction Ensemble Approach
Stéphane Dupont and Thierry Ravet
University of Mons, Belgium

A Study of Ensemble Synchronisation Under Restricted Line of Sight
Bogdan Vera, Elaine Chew and Patrick G. T. Healey
Queen Mary University of London, UK

Groove Kernels as Rhythmic-Acoustic Motif Descriptors
Andy Sarroff and Michael Casey
Dartmouth College, USA

Instrument Identification Informed Multi-Track Mixing
Jeffrey Scott and Youngmoo E Kim
Drexel University, USA

Tempo Detection of Urban Music Using Tatum Grid Non Negative Matrix Factorization
Daniel Gärtner
Fraunhofer Institute for Media Technology, Germany

A Study of Cultural Dependence of Perceived Mood in Greek Music
Katerina Kosta, Yading Song, Gyorgy Fazekas and Mark Sandler
Queen Mary University of London, UK

Evaluation on Feature Importance for Favorite Song Detection
Yajie Hu, Dingding Li and Mitsunori Ogihara
University of Miami, USA

QBT-Extended: An Annotated Dataset of Melodically Contoured Tapped Queries
Blair Kaneshiro, Hyung-Suk Kim, Jorge Herrera, Jieun Oh, Jonathan Berger and Malcolm Slaney
Stanford University, USA | Microsoft Research, USA

Audio Chord Recognition with Recurrent Neural Networks
Nicolas Boulanger-Lewandowski, Yoshua Bengio and Pascal Vincent
University of Montreal, Canada

Virtualband: Interacting with Stylistically Consistent Agents
Julian Moreira, Pierre Roy and François Pachet
Sony CSL, France

Wednesday Nov.6 – 12:40-14:00
Lunch

99 Brasserie Café (1st floor)

Wednesday Nov.6 – 14:00:15:00
OS4: Music Signal Analysis

Bourbon Auditorium (1st floor)

Sparse Modeling for Artist Identification: Exploiting Phase Information and Vocal Separation
Li Su and Yi-Hsuan Yang
Academia Sinica, Taiwan

Automatic Transcription of Turkish Makam Music
Emmanouil Benetos and Andre Holzapfel
City University London, UK | Bogazici University, Turkey

Local Group Delay Based Vibrato and Tremolo Suppression for Onset Detection
Sebastian Böck and Gerhard Widmer
Johannes Kepler University, Austria

Wednesday Nov.6 – 15:00-16:20
PS2: Poster Session 2 Cont.

All Seasons Hall (ground floor)

Wednesday Nov.6 – 16:20-17:20
OS5: Source Identification And Separation

Bourbon Auditorium (1st floor)

Beyond NMF: Time-Domain Audio Source Separation without Phase Reconstruction
Kazuyoshi Yoshii, Ryota Tomioka, Daichi Mochihashi and Masataka Goto
National Institute of Advanced Industrial Science and Technology, Japan | The University of Tokyo, Japan | The Institute of Statistical Mathematics, Japan

Beta Process Sparse Nonnegative Matrix Factorization for Music
Dawen Liang, Matthew D. Hoffman and Daniel P. W. Ellis
Columbia University, USA | Adobe Research, USA

Semi-Supervised Polyphonic Source Identification using PLCA Based Graph Clustering
Vipul Arora and Laxmidhar Behera
Indian Institute of Technology, India

Wednesday Nov.6 – 17:20-18:20
Industrial Panel

Bourbon Auditorium (1st floor)

Thursday Nov.7 – 9:00-10:20
OS6: Listeners

Bourbon Auditorium (1st floor)

An Experiment about Estimating the Number of Instruments in Polyphonic Music: A Comparison Between Internet and Laboratory Results
Michael Schoeffler, Fabian-Robert Stöter, Harald Bayerlein, Bernd Edler and Jürgen Herre
International Audio Laboratories Erlangen, Germany

Social-EQ: Crowdsourcing an Equalization Descriptor Map
Mark Cartwright and Bryan Pardo
Northwestern University, USA

Taste Over Time: The Temporal Dynamics of User Preferences
Joshua Moore, Shuo Chen, Douglas Turnbull and Thorsten Joachims
Cornell University, USA | Ithaca College, USA

Exploring the Relation Between Novelty Aspects and Preferences in Music Listening
Andryw Marques Ramos, Nazareno Andrade and Leandro Balby Marinho
Federal University of Campina Grande, Brazil

Thursday Nov.7 – 10:20-11:00
Poster Craze

Bourbon Auditorium (1st floor)

Thursday Nov.7 – 11:00-12:40 and 15:00-16:20
PS3: Poster Session 3

All Seasons Hall (ground floor)

Spectral Correlates in Emotion Labeling of Sustained Musical Instrument Tones
Bin Wu, Simon Wun, Chung Lee and Andrew Horner
Hong Kong University of Science and Technology, Hong Kong | Singapore University of Technology and Design, Singapore

Design and Evaluation of Semantic Mood Models for Music Recommendation using Editorial Tags
Mathieu Barthet, David Marston, Chris Baume, Gyorgy Fazekas and Mark Sandler
Queen Mary University of London, UK | BBC R&D London, UK

Low-Rank Representation of Both Singing Voice and Music Accompaniment Via Learned Dictionaries
Yi-Hsuan Yang
Academia Sinica, Taiwan

Incremental Visualization of Growing Music Collections
Sebastian Stober, Thomas Low, Tatiana Gossen and Andreas Nürnberger
University of Magdeburg, Germany

Evaluating OMR on the Early Music Online Collection
Laurent Pugin and Tim Crawford
Swiss RISM Office, Switzerland | Goldsmiths College University of London, UK

Sparse Music Decomposition onto a MIDI Dictionary Driven by Statistical Music Knowledge
Boyang Gao, Emmanuel Dellandréa and Liming Chen
Université de Lyon, CNRS, France | Ecole Centrale de Lyon, LIRIS, France

Annotating Works for Music Education: Propositions for a Musical Forms and Structures Ontology and a Musical Performance Ontology
Véronique Sébastien, Didier Sébastien and Noël Conruyt
University of Reunion Island, Réunion

Chord-Sequence-Factory: A Chord Arrangement System Modifying Factorized Chord Sequence Probabilities
Satoru Fukayama, Kazuyoshi Yoshii and Masataka Goto
National Institute of Advanced Industrial Science and Technology, Japan

Music Cut and Paste: A Personalized Musical Medley Generating System
I-Ting Liu, Yin-Tzu Lin and Ja-Ling Wu
National Taiwan University, Taiwan

A Meta-Analysis of the MIREX Structural Segmentation Task
Jordan Smith and Elaine Chew
Queen Mary University of London, UK

A Deterministic Annealing EM Algorithm for Automatic Music Transcription
Tian Cheng, Simon Dixon and Matthias Mauch
Queen Mary University of London, UK

Modelling the Speed of Music using Features from Harmonic/Percussive Separated Audio
Anders Elowsson, Anders Friberg, Guy Madison and Johan Paulin
KTH Royal Institute of Technology, Sweden | Umeå University, Sweden

Inter and Intra Item Segmentation of Continuous Audio Recordings of Carnatic Music for Archival
Padi Sarala and Hema A. Murthy
IIT Madras, India

Essentia: An Audio Analysis Library for Music Information Retrieval
Dmitry Bogdanov, Nicolas Wack, Emilia Gómez, Sankalp Gulati, Perfecto Herrera, Oscar Mayor, Gerard Roma, Justin Salamon, José R. Zapata and Xavier Serra
Universitat Pompeu Fabra, Spain

Motif Spotting in an Alapana in Carnatic Music
Vignesh Ishwar, Shrey Dutta, Ashwin Bellur and Hema Murthy
IIT Madras, India

Empirical Analysis of Track Selection and Ordering in Electronic Dance Music using Audio Feature Extraction
Thor Kell and George Tzanetakis
McGill University, Canada | University of Victoria, Canada

Improving the Reliability of Music Genre Classification using Rejection and Verification
Alessandro Koerich
Pontifical University Catholic of Parana, Brazil

Robotaba Guitar Tablature Transcription Framework
Gregory Burlet and Ichiro Fujinaga
McGill University, Canada

Comparing Onset Detection & Perceptual Attack Time
Richard Polfreman
University of Southampton, UK

K-Pop Genres: A Cross-Cultural Exploration
Jin Ha Lee, Kahyun Choi, Xiao Hu and J. Stephen Downie
University of Washington, USA | University of Illinois, USA | University of Hong Kong, Hong Kong

Coupling Social Network Services and Support for Online Communities in Codes Environment
Felipe Mendonça Scheeren, Marcelo Soares Pimenta, Damián Keller and Victor Lazzarini
Federal University of Rio Grande do Sul, Brazil | Federal University of Acre, Brazil | National University of Ireland, Ireland

Basic Evaluation of Auditory Temporal Stability (Beats): A Novel Rationale and Implementation
Zhouhong Cai, Robert J. Ellis, Zhiyan Duan, Hong Lu and Ye Wang
National University of Singapore, Singapore | Fudan University, China

Thursday Nov.7 – 12:40-14:00
Lunch

99 Brasserie Café (1st floor)

Thursday Nov.7 – 14:00:15:00
OS7: Symbolic Data Processing

Bourbon Auditorium (1st floor)

SIARCT-CFP: Improving Precision and the Discovery of Inexact Musical Patterns in Point-Set Representations
Tom Collins, Andreas Arzt, Sebastian Flossmann and Gerhard Widmer
Johannes Kepler University, Austria

A Machine Learning Approach to Voice Separation in Lute Tablature
Reinier de Valk, Tillman Weyde and Emmanouil Benetos
City University London, UK

A Methodology for the Comparison of Melodic Generation Models Using Meta-Melo
Nicolas Gonzalez Thomas, Philippe Pasquier, Arne Eigenfeldt and James B. Maxwell
Simon Fraser University, Canada

Thursday Nov.7 – 15:00-16:20
PS3: Poster Session 3 Cont.

All Seasons Hall (ground floor)

Thursday Nov.7 – 16:20-17:20
OS8: Music Similarity

Bourbon Auditorium (1st floor)

An Extended Audio Fingerprint Method with Capabilities for Similar Music Detection
Sébastien Fenet, Yves Grenier and Gaël Richard
Télécom ParisTech, France

AutoMashUpper: An Automatic Multi-Song Mashup System
Matthew Davies, Philippe Hamel, Kazuyoshi Yoshii and Masataka Goto
National Institute of Advanced Industrial Science and Technology, Japan

Learning Binary Codes For Efficient Large-Scale Music Similarity Search
Jan Schlüter
Austrian Research Institute for Artificial Intelligence, Austria

Thursday Nov.7 – 20:00-22:00
Conference Dinner

Restaurante Madalosso


Friday Nov.8 – 9:00-10:20
OS9: Structure and Form

Bourbon Auditorium (1st floor)

Freischuetz Digital: A Case Study for Reference-Based Audio Segmentation for Operas
Thomas Praetzlich and Meinard Mueller
International Audio Laboratories Erlangen, Germany

Automated Methods for Analyzing Music Recordings in Sonata Form
Nanzhu Jiang and Meinard Mueller
International Audio Laboratories Erlangen, Germany

Combining Harmony-Based and Novelty-Based Approaches for Structural Segmentation
Johan Pauwels, Florian Kaiser and Geoffroy Peeters
STMS IRCAM-CNRS-UPMC, France

Automatic Alignment of Music Performances with Structural Differences
Maarten Grachten, Martin Gasser, Andreas Arzt and Gerhard Widmer
Austrian Research Institute for Artificial Intelligence, Austria | Johannes Kepler Universitat, Austria

Friday Nov.8 – 14:00-18:00

Late-Breaking News and Demos

Maragogipe Room, Sumatra Room, Catuí Room, Foyer (2st floor)

LBD 1: A Brief Review of Creative MIR
Eric J. Humphrey, Douglas Turnbull and Tom Collins

LBD 2: Well-defined tasks and good datasets for MIR
Eric Battemberg

LBD 4: Digital Musicology and MIR: Papers, Projects and Challenges
Frans Wiering and Emmanouil Benetos

LBD 6: 2013 Late-break Session on Music Segmentation
Oriol Nieto and Jordan B. L. Smith

 

 

 

GeneralMap2

  1. Bourbon Hotel and Convention Center (Main Venue)
  2. Trevi Hotel
  3. Hotel Del Rey
  4. Hotel Tibagi
  5. Slaviero Slim Centro
  6. L’Avenue Apart Hotel
  7. Garibaldi Palace (Welcome Reception)