Computer Music Reading Group

Every Thursday 4:00 to 5:00 pm EST time @ GHC 4301
Online Meeting @

We discuss papers on music learning, understanding, representations, generation, and signal processing, with an emphasis on machine learning. We welcome anyone to join us. To sign up our reading group mailing list please click here .

If you have any idea, comment or suggestion, email us at .

Computer Music Group ,
Computer Science Department,
Carnegie Mellon University


[2023 Nov 30] ISMIR 2023 paper discussion session 2

[2023 Nov 16] ISMIR 2023 paper discussion session 1

[2023 Nov 2] LLark: A Multimodal Foundation Model for Music
     presented by Chris Donahue

[2023 Oct 5] Why we need a Symbolic Music LLM and its potential in music production
     presented by Yi Wang

[2023 Sep 28] The Beauty of Repetition: an Algorithmic Composition Model with Motif-level Repetition Generator and Outline-to-music Generator in Symbolic Music Generation
     presented by Roger B. Dannenberg

[2023 Sep 21] LLMs in music workflows: NeuralMidiFx, MusicGen, Anticipatory Music Transformer
     presented by Chris Donahue

[2023 Sep 7] Overview of Singing Voice Synthesis
     presented by Shuqi Dai

[2022 April 20] Neural Instrument Cloning from very few samples
     presented by Nicolas Jonason

[2022 April 13] MIDI-DDSP: Detailed Control of Musical Performance via Hierarchical Modeling
     presented by Yusong Wu

[2022 April 1] AI music generation with repetition structure
     presented by Shuqi Dai

[2022 March 16] ISMIR paper discussion: Poster Session 3

[2022 Feb 16] ISMIR paper discussion: Poster Session 3

[2022 Jan 19 & Jan 26 & Feb 2] ISMIR paper discussion: Poster Session 2

[2021 Dec 15] ISMIR paper discussion: Poster Session 2

[2021 Dec 8] ISMIR paper discussion: Poster Session 1

[2021 Dec 1] ISMIR paper discussion: Poster Session 1

[2021 Sep 29] Computational analysis and modeling of expressive timing in Chopin's Mazurkas
     presented by Zhengshan (Kitty) Shi

[2021 Sep 15] Timbre as spectral envelope
     presented by Daniel Qin

[2021 Sep 8] Learn by Referencing: Towards Deep Metric Learning for Singing Assessment
     presented by Huan Zhang

[2021 Aug 25] AccoMontage: Accompaniment Arrangement via Phrase Selection and Style Transfer
     presented by Jingwei Zhao

[2021 Aug 11] TONet: Tone-Octave Network for Singing Melody Extraction from Polyphonic Music
     presented by Ke Chen

[2021 Aug 4] Symbolic Music Generation via Music Frameworks
     presented by Shuqi Dai

[2021 July 28] A Unified Model For Zero-shot Music Source Separation, Transcription and Synthesis
     presented by Liwei Lin and Qiuqiang Kong

[2021 Feb 24] Universality and Diversity in Human Song
     presented by Shuqi Dai

[2020 Dec 23] Small Tricks, Grand Design: Learning Interpretable Music Representations Using Inductive Bias
     presented by Gus Xia

[2020 Dec 16] Improved Handling of Repeats and Jumps in Audio-Sheet Image Synchronization
     presented by Mengyi Shan

[2020 Dec 9] Few-shot Drum Transcription in Polyphonic Music
     presented by Yu Wang

[2020 Dec 2] Generating Music with a Self-correcting Non-chronological Autoregressive Model
     presented by Wayne Chi and Prachi Kumar

[2020 Nov 18] Harmonic Profile Project — An online tool for 3D visualization and analysis of triadic harmony
     HPP demo on YouTube
     presented by Federico Garcia-De Castro

[2020 Nov 11] GiantMIDI-Piano: A large-scale MIDI dataset for classical piano music
     High-resolution Piano Transcription with Pedals by Regressing Onsets and Offsets Times
     presented by Qiuqiang Kong

[2020 Sep 16] Automatic Detection of Hierarchical Structure and Influence of Structure on Melody, Harmony and Rhythm in Popular Music
     presented by Shuqi Dai

[2020 Sep 2] Automated Methods for Analyzing Music Recordings in Sonata Form
     SIARCT-CFP: Improving Precision and the Discovery of Inexact Musical Patterns in Point-Set Representations
     SE and SNL diagrams: Flexible data structures for MIR
     presented by Shuqi Dai

[2020 Aug 19] Visually Grounded Neural Syntax Acquisition
     presented by Haoyue Shi

[2020 Aug 12] Language Models are Few-Shot Learners discussion with researchers from NLP area

[2020 July 29] Beneath (or beyond) the surface: Discovering voice-leading patterns with skip-grams
     presented by Roger B. Dannenberg

[2020 July 22] Generating Sentences by Editing Prototypes
     hosted by Shuqi Dai

[2020 July 8] Music transcription modelling and composition using deep learning
     presented by Shuqi Dai

[2020 July 1] MuseGAN: Multi-track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompaniment
     presented by Shuqi Dai

[2020 June 17] Learning Controllable Representation of Polyphonic Music
     presented by Ziyu Wang

[2020 June 10] MelNet: A Generative Model for Audio in the Frequency Domain
     presented by Zeyu Jin

[2020 June 3] Jukebox: A Generative Model for Music
     hosted by Shuqi Dai

[2020 May 27] Harmonic Analysis of Music Using Combinatory Categorial Grammar
     presented by Shuqi Dai

[2020 April 29] Interactive Rainbow Score: A Visual-centered Multimodal Flute Tutoring System
     presented by Gus Xia

[2020 April 22] Implicit Generation and Modeling with Energy-Based Models
     Generative Modeling by Estimating Gradients of the Data Distribution
     presented by Junyan Jiang

[2020 April 1] Deep Voice Conversion
     Chapter 4 Deep-VoCo: word synthesis based on deep neural networks
     presented by Zeyu Jin

[2020 March 25] Conditional Variational Autoencoders
     Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders
     T-CVAE: Transformer-Based Conditioned Variational Autoencoder for Story Completion
     A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues
     presented by Ziyu Wang

[2020 March 18] Correlated Variational Auto-Encoders
     presented by Dawen Liang

[2020 March 11] Music Data Augmentation
     presented by Shuqi Dai

[2020 March 4] Deep Fragment Embeddings for Bidirectional Image Sentence Mapping
     presented by Gus Xia

[2020 Feb 26] Pattern Discovery and Music Similarity with Compositional Hierarchical Model
     A Compositional Hierarchical Model For Music Information Retrieval
     presented by Roger B. Dannenberg

[2019 Nov 21] Generating Structured Drum Pattern Using Variational Autoencoder and Self-Similarity Matrix
    presented by Junyan Jiang

[2019 Nov 14] Modeling Music Modality With A Key-Class Variant Pitch Chroma CNN
    presented by Shuqi Dai

[2019 Oct 31] David Cope: Music Style Representation from Computers and Musical Style
    presented by Shuqi Dai

[2019 Oct 24] Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
     presented by Junyan Jiang

[2019 Oct 17] Rethinking Recurrent Latent Variable Model for Music Composition
     Pattern Discovery From Audio Recordings By Variable Markov Oracle: A Music Information Dynamics Approach
     presented by Roger B. Dannenberg

[2019 Oct 3] Adaptive Multimodal Music Learning via Interactive-haptic Instrument
    presented by the paper author Gus Xia

[2019 Sep 26] Music Evaluation Survey
     Reference paper: On the Evaluation of Generative Models in Music
     presented by Shuqi Dai

[2019 Sep 19] MidiMe: Personalizing MusicVAE
     presented by Shuqi Dai

[2019 April 24] Sampling Theory in Music Information Retrieval part 2
    presented by Roger B. Dannenberg

[2019 April 17] Sampling Theory in Music Information Retrieval part 1
    presented by Roger B. Dannenberg

[2019 April 10] Music Transformer: Generating Music With Long-Term Structure
    presented by Zheng Jiang

[2019 April 3] Reinforcement Learning in Automatic Music Generation - part 2
     SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient
    presented by Junyan Jiang

[2019 March 27] Reinforcement Learning in Automatic Music Generation - part 1
     Tuning Recurrent Neural Networks With Reinforcement Learning
    presented by Shuqi Dai