Shreyan Chowdhury

Curriculum Vitae

Reach out to me at: shreyan0311 [at] gmail [dot] com

Shreyan Chowdhury

Highlights

Latest paper

Latest paper

DExter: Learning and controlling performance expression with diffusion models

PDF Demo Code
Real-time musical emotion tracking

Real-time musical emotion tracking

Predicting Jacob Collier's musical emotions through his piano playing

YouTube Video
My PhD Thesis

My PhD Thesis

Modelling Emotional Expression in Music Using Interpretable and Transferable Perceptual Features

PDF
Magazine Article

Magazine Article

My research covered in IIT Madras Shaastra Magazine

Article
My most-cited paper

My most-cited paper

Towards Explainable Music Emotion Recognition: The Route via Mid-level Features

PDF
Patent on audio-based predictive maintenance

Patent on audio-based predictive maintenance

Monitoring industrial equipment using audio

Patent PDF

Experience

Co-Founder and Chief Science Officer

SongForm, Inc. | Remote Nov 2023 - Present

Machine Learning Consultant (Contract)

Bogren Digital | Remote May 2023 - Nov 2023

Postdoctoral Researcher

Johannes Kepler University Linz | Linz, Austria Jan 2023 - Dec 2023

Scientific Staff (PhD researcher)

Johannes Kepler University Linz | Linz, Austria May 2018 - Dec 2022

Product Design Engineer

Honeywell Technology Solutions | Bangalore, India July 2015 - May 2018


Education

Ph.D. in Computer Science

Johannes Kepler University Linz | Linz, Austria May 2018 - Dec 2022

M.Tech. + B.Tech. (Dual Degree) in Electrical Engineering

Indian Institute of Technology Kanpur (IIT-Kanpur) | Kanpur, India Jul 2010 - Jul 2015


Publications

  1. DExter: Learning and controlling performance expression with diffusion models. [HTML] [PDF] [Demo] [Code]
    H Zhang, S Chowdhury, CE Cancino-Chacón, J Liang, S Dixon, G Widmer (2024).
    MDPI Applied Sciences, 14(15), 6543.

  2. Expressivity-aware Music Performance Retrieval using Mid-level Perceptual Features and Emotion Word Embeddings. [PDF]
    S Chowdhury, G Widmer (2023).
    Proceedings of the 15th Annual Meeting of the Forum for Information, Goa, India.

  3. Are we describing the same sound? An analysis of word embedding spaces of expressive piano performance. [PDF]
    SD Peter, S Chowdhury, CE Cancino-Chacón, G Widmer (2023)
    Proceedings of the 15th Annual Meeting of the Forum for Information, Goa, India.

  4. Decoding and Visualising Intended Emotion in an Expressive Piano Performance. [PDF] [Demo Video]
    S Chowdhury, G Widmer (2022)
    ISMIR. Late-Breaking Demo Session of the 23rd Int. Society for Music Information Retrieval Conf., Bengaluru, India

  5. Modelling emotional expression in music using interpretable and transferable perceptual features. [PDF]
    S Chowdhury (2022)
    Ph. D. Thesis.

  6. On perceived emotion in expressive piano performance: Further experimental evidence for the relevance of mid-level perceptual features.
    S Chowdhury, G Widmer
    arXiv preprint arXiv:2107.13231.

  7. Tracing Back Music Emotion Predictions to Sound Sources and Intuitive Perceptual Qualities.
    S Chowdhury, V Praher, G Widmer
    Proceedings of the 18th Sound and Music Computing Conference, 246-252.

  8. Towards explaining expressive qualities in piano recordings: Transfer of explanatory features via acoustic domain adaptation.
    S Chowdhury, G Widmer
    ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and.

  9. Receptive-field regularized CNNs for music classification and tagging.
    K Koutini, H Eghbal-Zadeh, V Haunschmid, P Primus, S Chowdhury, …
    arXiv preprint arXiv:2007.13503.

  10. On the Characterization of Expressive Performance in Classical Music: First Results of the Con Espressione Game.
    C Cancino-Chacón, S Peter, S Chowdhury, A Aljanaki, G Widmer
    Proceedings of the 21st International Society for Music Information.

  11. Monitoring industrial equipment using audio.
    R Yelchuru, S Chowdhury, P Sampath
    US Patent 10,475,468.

  12. Emotion and theme recognition in music with frequency-aware RF-regularized CNNs.
    K Koutini, S Chowdhury, V Haunschmid, H Eghbal-Zadeh, G Widmer
    arXiv preprint arXiv:1911.05833.

  13. Two-level Explanations in Music Emotion Recognition.
    V Haunschmid, S Chowdhury, G Widmer
    International Conference on Machine Learning (ICML), Machine Learning for.

  14. Towards Explainable Music Emotion Recognition: The Route via Mid-level Features.
    S Chowdhury, A Vall, V Haunschmid, G Widmer
    Proceedings of the 20th International Society for Music Information.

  15. Music tempo estimation using sub-band synchrony.
    S Chowdhury, T Guha, RM Hegde
    Proceedings of Interspeech 2017, 3093-3096.

  16. Musical Tempo Estimation from Audio using Sub-Band Synchrony.
    S Chowdhury
    INDIAN INSTITUTE OF TECHNOLOGY, KANPUR.

Certifications

Achievements

Service

Languages

Hobbies