Poster Sessions

Paper Session - 7

Session Chair: ‪Gaël Richard (Télécom Paris)

2022-12-08 | 09:00 (Asia/Calcutta)

Browse the active poster session's channels, joining calls to ask questions and discuss research with presenters, and leave comments in the channel for asynchronous chatting later.

  • P7-01: A unified model for zero-shot singing voice conversion and synthesis
    Jui-Te Wu, Jun-You Wang, Jyh-Shing Roger Jang, Li Su
  • P7-02: Semantic Control of Generative Musical Attributes
    Stewart Greenhill, Majid Abdolshah, Vuong Le, Sunil Gupta, Svetha Venkatesh
  • P7-03: Music Representation Learning Based on Editorial Metadata from Discogs
    Pablo Alonso-Jiménez, Xavier Serra, Dmitry Bogdanov
  • P7-04: Melody Infilling with User-Provided Structural Context
    Chih-Pin Tan, Alvin W Y Su, Yi-Hsuan Yang
  • P7-05: Robust Melody Track Identification in Symbolic Music
    Xichu Ma, Xiao Liu, Bowen Zhang, Ye Wang
  • P7-06: Tracking the Evolution of a Band's Live Performances over Decades
    Florian Thalmann, Eita Nakamura, Kazuyoshi Yoshii
  • P7-07: Evaluating Generative Audio Systems and Their Metrics
    Ashvala Vinay, Alexander Lerch
  • P7-08: Representation Learning for the Automatic Indexing of Sound Effects Libraries
    Alison B Ma, Alexander Lerch
  • P7-09: Concept-Based Techniques for ""Musicologist-Friendly"" Explanations in Deep Music Classifiers
    Francesco Foscarin, Katharina Hoedt, Verena Praher, Arthur Flexer, Gerhard Widmer
  • P7-10: Verse versus Chorus: Structure-aware Feature Extraction for Lyrics-based Genre Recognition
    Maximilian Mayerl, Stefan Brandl, Günther Specht, Markus Schedl, Eva Zangerle
  • P7-11: Transfer Learning of wav2vec 2.0 for Automatic Lyric Transcription
    Longshen Ou, Xiangming Gu, Ye Wang
  • P7-12: A Novel Dataset and Deep Learning Benchmark for Classical Music Form Recognition and Analysis
    Daniel Szelogowski, Lopamudra Mukherjee, Benjamin Whitcomb
  • P7-13: BAF: An audio fingerprinting dataset for broadcast monitoring
    Guillem Cortès, Alex Ciurana, Emilio Molina, Marius Miron, Owen Meyers, Joren Six, Xavier Serra
  • P7-14: Cadence Detection in Symbolic Classical Music using Graph Neural Networks
    Emmanouil Karystinaios, Gerhard Widmer
  • P7-15: Domain Adversarial Training on Conditional Variational Auto-Encoder for Controllable Music Generation
    Jingwei Zhao, Gus Xia, Ye Wang
  • P7-16: Modeling perceptual loudness of piano tone: theory and applications
    Yang Qu, Yutian Qin, Lecheng Chao, Hangkai Qian, Ziyu Wang, Gus Xia
  • P7-17: On the Impact and Interplay of Input Representations and Network Architectures for Automatic Music Tagging
    Maximilian Damböck, Richard Vogl, Peter Knees

An asterisk (*) indicates long presentations (paper award candidates)

Industry Session

Industry Session

Session Chair: Siddharth Bhardwaj (

2022-12-08 | 11:30 (Asia/Calcutta)

Industry presentation session will include short presentations from our industry sponsors. The session will have a 12 min talks by our Platinum sponsors Spotify and Moises, and 8 min talks by our Gold sponsors Adobe, Deezer, Utopia music, Pandora, Smule, Yamaha and Chordify.

Business Meeting and Awards

Society meeting, awards and closing

Session Chair: Geoffroy Peeters (IRCAM, Télécom Paris)

2022-12-08 | 13:30 (Asia/Calcutta)

Society meeting, awards and closing

Late Breaking Demo