Latest news Latest news

Return to Full Page

MIP-Frontiers Final Workshop

MIP-Frontiers Final Workshop

The project New Frontiers in Music Information Processing (MIP-Frontiers), funded by Marie Skłodowska-Curie ITN program, presents its results


Imatge inicial

MIP-Frontiers project (New Frontiers in Music Information Processing) has supported 15 PhD students at four universities working with a range of industry and cultural partners. This final workshop allows the fellows to present the main results of their research over the last three years. Invited researchers in the field will also participate with keynote presentations. The Music Technology Group is part of this project, with 3 PhD students participating: António Ramires, Philip Tovstogan, Furkan Yesiler.

Date: Thursday 15th - Friday 16th of October 2021

Time Zone: UTC+01 (UK time)

Location: Online (Zoom link)

Thursday 14th October 2021

9:00 Welcome
  Simon Dixon, Queen Mary University of London
  Domna Paschalidou, European Research Executive Agency
9:15 Data-Driven Musical Version Identification: Accuracy, Scalability, and Bias Perspectives
  Furkan Yesiler, Universitat Pompeu Fabra
  Deep Learning Methods for Musical Instrument Separation and Recognition
  Carlos Lordelo, Queen Mary University of London & DoReMIR
10:30 Informed Audio Source Separation with Deep Learning in Limited Data Settings
  Kilian Schulze-Forster, Telecom Paris
  Deep Neural Networks for Automatic Lyrics Transcription
  Emir Demirel, Queen Mary University of London
11:45 Data-Driven Approaches for Query by Vocal Percussion
  Alejandro Delgado, Queen Mary University of London & Roli
12:15 Lunch Break
14:00 Keynote 1: Applications of Machine Intelligence in Computational Acoustics
  Augusto Sarti, Politecnico di Milano
15:00 Towards Neural Context-Aware Performance-Score Synchronization
  Ruchit Agrawal, Queen Mary University of London
  Autonomous and Robust Live Tracking of Complete Opera Performances
  Charles Brazier, Johannes Kepler University Linz
16:15 Large-Scale Multi-Modal Music Search and Retrieval without Symbolic Representation
  Luís Carvalho, Johannes Kepler University Linz
  Robust Deep Learning for Music Performance Analysis
  Vinod Subramanian, Queen Mary University of London

Friday 15th October 2021

9:00 Keynote 2: Source Separation Metrics: What are they really capturing?
  Rachel Bittner, Spotify
10:00 Exploration of Music Collections with Audio Embeddings
  Philip Tovstogan, Universitat Pompeu Fabra
  Audio Auto-tagging as Proxy for Contextual Music Recommendation
  Karim Ibrahim, Telecom Paris
11:15 Deep Learning Methods for Music Style Transfer
  Ondřej Cífka, Telecom Paris
  Exploring Generative Adversarial Networks for Controllable Musical Audio Synthesis
  Javier Nistal, Telecom Paris & Sony SCL
12:15 Lunch Break
14:00 Keynote 3: Generative Modeling Meets Deep Learning: A Modern Statistical Approach to Music Signal Analysis
  Kazuyoshi Yoshii, Kyoto University
15:00 Neuro-Steered Music Source Separation
  Giorgia Cantisani, Telecom Paris
  Automatic Characterization and Generation of Music Loops and Instrument Samples for Electronic Music Production
  António Ramires, Universitat Pompeu Fabra
16:00 Closing
  Domna Paschalidou, European Research Executive Agency