README.md

ISMIR-2023-Papers

---

ISMIR 2023 Papers: A complete collection of influential and exciting research papers from the ISMIR 2023 conference. Explore the latest advances in Music information retrieval. Code included. ⭐

👉 * This count includes repositories on GitHub, GitLab, Hugging Face, and distributions on PyPI, while excluding Web Page or GitHub Page links.

---

The PDF version of the ISMIR 2023 Conference Programme, comprises a list of all accepted full papers, their presentation order, as well as the designated presentation times.

---

Other collections of the best AI conferences

❗ Conference table will be up to date all the time.

Conference	Year
	2023
Computer Vision (CV)
CVPR
ICCV
Speech/Signal Processing (SP/SigProc)
ICASSP
INTERSPEECH

---

Contributors

Contributions to improve the completeness of this list are greatly appreciated. If you come across any overlooked papers, please feel free to create pull requests, open issues or contact me via email. Your participation is crucial to making this repository even better.

---

Tutorials

Title	Material
Analysing Physiological Data Collected During Music Listening: An Introduction
Introduction to Differentiable Audio Synthesizer Programming
Transformer-based Symbolic Music Generation: Fundamentals to Advanced Concepts, Stylistic Considerations, Conditioning Mechanisms and Large Language Models
Computer-Assisted Music-Making Systems: Taxonomy, Review, and Coding	➖
Learning with Music Signals: Technology Meets Education	➖
Kymatio: Deep Learning Meets Wavelet Theory for Music Signal Processing

---

Papers

List of sessions

• Session 1
• Session 2
• Session 3
• Session 4
• Session 5
• Session 6
• Session 7
• Late-Breaking Demo

Session 1

Title	Repo	Paper
Exploring the Correspondence of Melodic Contour with Gesture in Raga Alap Singing
TriAD: Capturing Harmonics with 3D Convolutions
Data Collection in Music Generation Training Sets: A Critical Analysis
A Review of Validity and its Relationship to Music Information Research
Segmentation and Analysis of Taniavartanam in Carnatic Music Concerts	➖
Transfer Learning and Bias Correction with Pre-Trained Audio Embeddings
Collaborative Song Dataset (CoSoD): An Annotated Dataset of Multi-Artist Collaborations in Popular Music
Human-AI Music Creation: Understanding the Perceptions and Experiences of Music Creators for Ethical and Productive Collaboration
Impact of Time and Note Duration Tokenizations on Deep Learning Symbolic Music Modeling
Musical Micro-Timing for Live Coding
A Few-Shot Neural Approach for Layout Analysis of Music Score Image
TapTamDrum: A Dataset for Dualized Drum Patterns
Real-Time Percussive Technique Recognition and Embedding Learning for the Acoustic Guitar
IteraTTA: An Interface for Exploring both Text Prompts and Audio Priors in Generating Music with Text-to-Audio Models
Similarity Evaluation of Violin Directivity Patterns for Musical Instrument Retrieval	➖
Polyrhythmic Modelling of Non-Isochronous and Microtiming Patterns	➖

Session 2

Title	Repo	Paper
CLaMP: Contrastive Language-Music Pre-Training for Cross-Modal Symbolic Music Information Retrieval
Gender-Coded Sound: Analysing the Gendering of Music in Toy Commercials via Multi-Task Learning
A Dataset and Baselines for Measuring and Predicting the Music Piece Memorability	➖
Efficient Notation Assembly in Optical Music Recognition	➖
White Box Search over Audio Synthesizer Parameters	➖
Decoding Drums, Instrumentals, Vocals, and Mixed Sources in Music using Human Brain Activity with fMRI	➖
Dual Attention-based Multi-Scale Feature Fusion Approach for Dynamic Music Emotion Recognition
Automatic Piano Transcription with Hierarchical Frequency-Time Transformer
High-Resolution Violin Transcription using Weak Labels
Polyffusion: A Diffusion Model for Polyphonic Score Generation with Internal and External Controls
The Coordinated Corpus of Popular Musics (CoCoPops): A Meta-Dataset of Melodic and Harmonic Transcriptions
Towards Computational Music Analysis for Music Therapy	➖
Timbre Transfer using Image-to-Image Denoising Diffusion Implicit Models
Correlation of EEG Responses Reflects Structural Similarity of Choruses in Popular Music	➖
Chromatic Chords in Theory and Practice	➖

Session 3

Title	Repo	Paper
BPS-Motif: A Dataset for Repeated Pattern Discovery of Polyphonic Symbolic Music
Weakly Supervised Multi-Pitch Estimation using Cross-Version Alignment
The Batik-Plays-Mozart Corpus: Linking Performance to Score to Musicological Annotations
Mono-to-Stereo through Parametric Stereo Generation	➖
From West to East: Who Can Understand the Music of the Others Better?	➖
On the Performance of Optical Music Recognition in the Absence of Specific Training Data	➖
Composer's Assistant: An Interactive Transformer for Multi-Track MIDI Infilling
The FAV Corpus: An Audio Dataset of Favorite Pieces and Excerpts, with Formal Analyses and Music Theory Descriptors
LyricWhiz: Robust Multilingual Lyrics Transcription by Whispering to ChatGPT
Sounds Out of Pläce? Score Independent Detection of Conspicuous Mistake Regions in MIDI Piano Performances
VampNet: Music Generation via Masked Acoustic Token Modeling
Expert and Novice Evaluations of Piano Performances: Criteria for Computer-Aided Feedback	➖
Contrastive Learning for Cross-Modal Artist Retrieval	➖
Repetition-Structure Inference with Formal Prototypes
Algorithmic Harmonization of Tonal Melodies using Weighted Pitch Context Vectors
Text-to-Lyrics Generation with Image-based Semantics and Reduced Risk of Plagiarism

Session 4

Title	Repo	Paper
LP-MusicCaps: LLM-based Pseudo Music Captioning
A Repetition-based Triplet Mining Approach for Music Segmentation	➖
Predicting Music Hierarchies with a Graph-based Neural Decoder
Stabilizing Training with Soft Dynamic Time Warping: A Case Study for Pitch Class Estimation with Weakly Aligned Targets
Finding Tori: Self-Supervised Learning for Analyzing Korean Folk Song
Singer Identity Representation Learning using Self-Supervised Techniques
On the Effectiveness of Speech Self-Supervised Learning for Music	➖
Transformer-based Beat Tracking with Low-Resolution Encoder and High-Resolution Decoder	➖
Adding Descriptors to Melodies Improves Pattern Matching: A Study on Slovenian Folk Songs	➖
How Control and Transparency for Users Could Improve Artist Fairness in Music Recommender Systems	➖
Towards a New Interface for Music Listening: A User Experience Study on YouTube	➖
FiloBass: A Dataset and Corpus based Study of Jazz Basslines
Comparing Texture in Piano Scores	➖
Introducing DiMCAT for Processing and Analyzing Notated Music on a Very Large Scale
Sequence-to-Sequence Network Training Methods for Automatic Guitar Transcription with Tokenized Outputs

Session 5

Title	Repo	Paper
PESTO: Pitch Estimation with Self-Supervised Transposition-Equivariant Objective
The Games we Play: Exploring the Impact of ISMIR on Musicology	➖
Carnatic Singing Voice Separation using Cold Diffusion on Training Data with Bleeding
Unveiling the Impact of Musical Factors in Judging a Song on First Listen: Insights from a User Survey
Towards Building a Phylogeny of Gregorian Chant Melodies	➖
Audio Embeddings as Teachers for Music Classification
ScorePerformer: Expressive Piano Performance Rendering with Fine-Grained Control
Roman Numeral Analysis with Graph Neural Networks: Onset-Wise Predictions from Note-Wise Features
Semi-Automated Music Catalog Curation using Audio and Metadata	➖
Crowd's Performance on Temporal Activity Detection of Musical Instruments in Polyphonic Music	➖
MoisesDB: A Dataset for Source Separation Beyond 4 Stems
Music as Flow: A Formal Representation of Hierarchical Processes in Music	➖
Online Symbolic Music Alignment with Offline Reinforcement Learning
InverSynthII: Sound Matching via Self-Supervised Synthesizer-Proxy and Inference-Time Finetuning
A Semi-Supervised Deep Learning Approach to Dataset Collection for Query-by-Humming Task
Towards Improving Harmonic Sensitivity and Prediction Stability for Singing Melody Extraction

Session 6

Title	Repo	Paper
Singing Voice Synthesis using Differentiable LPC and Glottalflow Inspired Wavetables
Harmonic Analysis with Neural Semi-CRF
A Dataset and Baseline for Automated Assessment of Timbre Quality in Trumpet Sound
Visual Overviews for Sheet Music Structure	➖
Passage Summarization with Recurrent Models for Audio – Sheet Music Retrieval	➖
Predicting Performance Difficulty from Piano Sheet Music Images
Self-Refining of Pseudo Labels for Music Source Separation with Noisy Labeled Data	➖
Quantifying the Ease of Playing Song Chords on the Guitar	➖
FlexDTW: Dynamic Time Warping with Flexible Boundary Conditions	➖
Modeling Bends in Popular Music Guitar Tablatures	➖
Self-Similarity-based and Novelty-based Loss for Music Structure Analysis
Modeling Harmonic Similarity for Jazz using Cooccurrence Vectors and the Membrane Area	➖
SingStyle111: A Multilingual Singing Dataset with Style Transfer
A Computational Evaluation Framework for Singable Lyric Translation	➖
Chorus-Playlist: Exploring the Impact of Listening to Only Choruses in a Playlist

Session 7

Title	Repo	Paper
Supporting Musicological Investigations with Information Retrieval Tools: An Iterative Approach to Data Collection	➖
Optimizing Feature Extraction for Symbolic Music
Exploring Sampling Techniques for Generating Melodies with a Transformer Language Model	➖
Measuring the Eurovision Song Contest: A Living Dataset for Real-World MIR
Efficient Supervised Training of Audio Transformers for Music Representation Learning
A Cross-Version Approach to Audio Representation Learning for Orchestral Music
Music Source Separation with MLP Mixing of Time, Frequency, and Channel	➖
Symbolic Music Representations for Classification Tasks: A Systematic Evaluation
The Music Meta Ontology: A Flexible Semantic Model for the Interoperability of Music Metadata
Polar Manhattan Displacement: Measuring Tonal Distances between Chords based on Intervallic Content	➖

Late-Breaking Demo

Title	Repo	Paper
Virtuoso Strings: A Dataset of String Ensemble Recordings and Onset Annotations for Timing Analysis
Music Scope Pad	➖
The Chordinator: Chord Progression Modeling and Generation using Transformers	➖
Cosine Contours: A Case Study with Melodies from Irish Traditional Dance Music	➖
AutoOsu: Audio-Aware Action Generation for Rhythm Games
Can MusicGen Create Training Data for MIR Tasks?	➖
Automatic Production of Acoustic Piano Transcription Data
MemoVision: A Tool for Feature Selection and Visualization of Performance Data
The Hi-Audio Online Platform for Distributed Music Crowdsourcing Database Collection	➖
On the use of Synthesized Datasets and Transformer Adaptors for Musical Instrument Recognition	➖
What Can Go Wrong When Conducting Beat Tracking Experiments
Bridging Audio and Symbolic Piano Data through a Web-based Annotation Interface
Towards Differentiable Piano Synthesis based on Physical Modeling
DJ StructFreak: Automatic DJ System Built with Music Structure Embeddings	➖
Generating Folk-Like Music in Abc-Notation with Masked Language Models
AQUATK: An Audio Quality Assessment Toolkit
Encoding Performance Data in MEI with the Automatic Music Performance Analysis and Comparison Toolkit (AMPACT)	➖
Retrieval Augmented Generation of Symbolic Music with LLMs
The Biased Journey of MSD_AUDIO.ZIP	➖
Fmak: A Dataset of Key and Mode Annotations for the Free Music Archive – Extended Abstract	➖
Orchestral Texture Classification with Convolution
Beat-Aligned Spectrogram-to-Sequence Generation of Rhythm-Game Charts
Total Variation in Popular Rap Vocals from 2009-2023: Extension of the Analysis by Georgieva, Ripollés & Mcfee
Towards Automated Estimation of Values from Song Lyrics: A Data Collection Protocol	➖
Track Role Prediction of Single-Instrumental Sequences	➖
Demo of a Smart Musical Instrument-based Real Time Pattern Detection System	➖
JamALT: A Formatting-Aware Lyrics Transcription Benchmark	➖
STraDa: A Singer Traits Dataset	➖
Interpretable Modular Representation Learning for Full-Band Accompaniment Arrangement	➖
Improving Embeddings in Harmony Transformer	➖
Singable and Controllable Neural Lyric Translation: A Late-Breaking Showcase	➖
A Noise Augmentation Pipeline for Realistic Query-by-Example Simulation
LARS: An Open-Source VST3 Plugin for Deep Drums Demixing with Pretrained Models
Music Visualization using Chironomie	➖
Automatic Transcription of Multi-Instrumental Songs: Integrating Demixing, Harmonic Dilated Convolution, and Joint Beat Tracking	➖
Mel-Band RoFormer for Music Source Separation	➖
THE VocalNotes DATASET	➖
From Taps to Drums: Audio Percussion Style Transfer	➖
JAMMIN-GPT: Text-based Improvisation using Llms in Ableton Live	➖
Visual Guitar Tab Comparison
Optimizing the Mridangam Stroke Transcription Pipeline: Addressing Key Challenges	➖

---

Star History