Late-breaking/Demo (LBD)

The Late-breaking/Demo (LBD) session is a forum for sharing prototype systems, initial concepts, and early results which may have not yet fully matured but are of interest to the Music-IR community. It is also a great entry point for people who are new to ISMIR to showcase their preliminary work and receive early feedback from fellow researchers. Attendees of the LBD can interact with demos or discuss their thoughts on the latest developments in the field.

Hybrid Conference

Similar to the main paper track, this year’s LBD will be held in a hybrid format, i.e., physical and remote. There will be two back-to-back sessions:

Physical session: Dec 8, 2022 (Thu), 3.30 pm - 5.30 pm
Virtual session: Dec 8, 2022 (Thu), 5.30 pm - 7.00 pm

Instructions to participants/attendees

Each LBD extended abstract will have a dedicated slack channel on the virtual platform and will have the abstract and poster / video on MiniConf.Both in -person and remote attendees can ask asynchronous questions to remote or in -person presenters via the slack channel.

Physical session: The LBD posters by in-person attendees will be presented during this session at the venue. Virtual presenters can choose to remain online to interact with any interested participants.
Remote session: Remote presenters can use the huddle feature on each LBD extended abstract slack channel to present their LBD posters on a video call. (Huddle supports up to 50 simultaneous participants).

Open Session

This year’s local LBD session is also an open session for students and independent researchers of the local community. The session will enable participants to attend the late-breaking/demo session of the conference and interact with students, experts and senior members of the ISMIR research community. This open session is a free registration event.

Accepted LBD submissions are below. More submissions to be added soon!

Hit Song Prediction for Indian Popular Music: Shreya Kale, Makarand Velankar, Rameshwari Joshi, Vaishnavi Ingole, Aparna Dhaygude
Audio Augmentations for Semi-Supervised Learning with FixMatch: Sascha Grollmisch, Estefanía Cano, Jakob Abeßer
libf0: A Python Library for Fundamental Frequency Estimation: Sebastian Rosenzweig, Simon J Schwär, Meinard Müller
Genre Classification and Analysis of Marathi Songs: Shreyas M Nadkarni, Preeti Rao
Towards Singer-independent Raga Classification from Audiovisual Recordings: Adbhut V Bhardwaj, Sujoy Roychowdhury, Preeti Rao
EGFxSet: Electric Guitar Tones Processed Through Real Effects of Distortion, Modulation, Delay and Reverb: Hegel Emmanuel Pedroza, Gerardo Meza, Iran R Roman
Generating Melodies with Controllable Similarity and Length in ABC Notation: Shangda Wu, Yuanliang Dong, Maosong Sun
Improving tokenization expressiveness with pitch intervals: Louis Bigo, Mikaela Keller
Visualizing Chord Recognition Performance: Christopher Liscio, Dan Brown
Towards modeling alternating patterns through inter-notes relations: Perrine Vantalon, Mathieu Giraud, Richard Groult, Thierry Lecroq
Exploring Popularity Bias in Music Steaming Services: Douglas Turnbull, Vera Crabtree, Sean McQuillan
Decoding and Visualising Intended Emotion in an Expressive Piano Performance: Shreyan Chowdhury, Gerhard Widmer
CCVS: A dataset for concert videography research: Hsin-Min Chou, Ting-Wei Lin, Jen-Chun Lin, Ching Te Chiu, Li Su
Augmented Reality Visualization for Musical Instrument Learning: Frank Heyen, Michael Sedlmair
AudioLoader: a hassle-free Pytorch audio dataset loader: Kin Wai Cheuk, Kwan Yee Heung, Dorien Herremans
A Web-Based MIDI Controller for Music Live Coding: Frank Heyen, Michael Sedlmair
Gamaka Synthesis for Kalpitha Swaras in Carnatic music: Raghavasimhan Sankaranarayanan, Gil Weinberg
SSM-NET: Feature Learning for Music Structure Analysis Using a Self-similarity-matrix Based Loss: Geoffroy Peeters, Florian Angulo
Differentiating the Pitch Bend Function Between the Sitar as a Real and Virtual Instrument: Suhit Chiruthapudi
Improvisation of tabla the indian percussion using fibre: Retnasree Iyer
On the Typicality of Music: Mathais Rose Bjare, Stefan Lattner
Towards a machine-learning approach to analyse the emotional impact of source localization in music: Eleonora De Filippi, Timothy Schmele, Arijit Nandi
A CHORD PROGRESSION LIBRARY FOR MEASURING EMOTIONS BY BCIs: Raffaella Folgieri, Enrico Daga, Claudio Lucchiari, Paul Arnold
Rapidly Predicting Music Artistic Expression Preference From Heart Rate and Respiration Rate: Shu Sakamoto, Vincent Cheung, Shinichi Furuya
MuSFA: Improving Music Structural Function Analysis with Partially Labeled Data: Ju-Chiang Wang, Jordan B. L. Smith, Yun-Ning Hung
Audio Metaphor 2.0: An Improved System for Automatic Sound Design: Renaud Bougueng Tchemeube, Joshua Kranabetter, Craig Carpenter, Philippe Pasquier, Miles Thorogood
Calliope: An Online Interface for Generative Music Co-Creation: Renaud Bougueng Tchemeube, Jeffrey Ens, Cale Plut, Philippe Pasquier
Western Music Notation for Java: A library for music notation on the JVM: Otso Björklund
A Multimodal Approach to Acoustic Guitar Strumming Action Transcription: Sebastian Murgul, Michael Heizmann
Midi-Draw: Sketching To Control Melody Generation: Tashi Namgyal
AI-driven, mobile-first web UI for controllable expressive piano performance composition: Théis Bazin, Gaëtan Hadjeres, Mikhail Malt
Beatoven.ai: AI-powered music creation: António Ramires, Siddharth Bhardwaj
Facets: A Tool For Management And Navigation Of Symbolic Music Collections: Tiange Zhu, Raphael Fournier-S'niehotta
Melody Slot Machine HD: Masatoshi Hamanaka
Assistive alignment of in-the-wild sheet music and performances: Michael Feffer, Chris Donahue, Zachary Lipton
Note level MIDI velocity estimation for piano performance: Hyon Kim, Marius Miron, Xavier Serra
Essentia API: a web API for music audio analysis: Albin Andrew Correya, Dmitry Bogdanov, Pablo Alonso-Jiménez, Xavier Serra
Differentiable WORLD Synthesizer-Based Neural Vocoder With Application To End-To-End Audio Style Transfer: Shahan Nercessian
Schmubert: A Symbolic Creative Harmonic Music Unmasking Bidirectional Encoder Representation Transformer: Matthias Plasser, Silvan Peter
Song Describer: a Platform for Collecting Textual Descriptions of Music Recordings: Ilaria Manco, Benno Weck, Philip Tovstogan, Minz Won, Dmitry Bogdanov
A Framework for Instrument Recognition Using Conditional Generative Adversarial Networks: Charis Cochran, Youngmoo Kim
Differentiable Acoustic Guitar Synthesis from Tablature: Andrew F Wiggins, Youngmoo Kim
A New Pianoroll With Relative Pitch Approach: Seonghyeon Go
Unsupervised Domain Adaptation For Sound Event Detection In Music Applications: Arkaprava Biswas, Akshay Raina, Vipul Arora
MAP-Music2Vec: A Simple and Effective Baseline for Self-Supervised Music Audio Representation Learning: Yizhi Li, Ruibin Yuan, Ge Zhang, Yinghao MA, Chenghua Lin, Xingran Chen, Anton Ragni, Hanzhi Yin, Zhijie Hu, Haoyu He, Emmanouil Benetos, Norbert Gyenge,Ruibo Liu, Jie Fu
CogXAI ANNalyzer: Cognitive Neuroscience Inspired Techniques for eXplainable AI: Maral Ebrahimzadeh, Valerie Krug, Sebastian Stober
A Family of Libraries for Working With Pitches and Intervals: Christoph Finkensiep, Robert Lieck, Martin A Rohrmeier
Audio Latent Space Cartography: Nicolas Jonason, Bob Sturm
DiscStitch: towards audio-to-audio alignment with robustness to playback speed variabilities: Joren Six
Neural Waveform Synthesis on a Low-Resource Embedded Device: Alexander Tipper

ISMIR 2022 logo designed by Mrinali Kamath and graphics designed by Vivek Vasudev