Papers & Patents 📝

publications by categories in reversed chronological order. generated by jekyll-scholar.

2025

  1. ISMIR
    Perceptual errors in Music Source Separation: looking beyond SDR averages
    Saurjya Sarkar, Victoria Moomjian, Basil Woods, Emmanouil Benetos, and Mark Sandler
    In 26th International Society for Music Information Retrieval Conference (ISMIR), 2025
    HTML
  2. ISMIR
    GOAT: A Large Dataset of Paired Guitar Audio Recordings and Tablatures
    Jackson Loth, Pedro Sarmento, Saurjya Sarkar, Zixun Guo, Mathieu Barthet, and Mark Sandler
    In 26th International Society for Music Information Retrieval Conference (ISMIR), 2025
    HTML

2024

  1. Thesis
    Time-domain music source separation for choirs and ensembles
    S Sarkar
    2024
    HTML

2023

  1. WASPAA
    Leveraging synthetic data for improving chamber ensemble separation
    S Sarkar, L Thorpe, E Benetos, and M Sandler
    In 2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), 2023
    HTML
  2. arXiv
    AI (r) evolution–where are we heading? Thoughts about the future of music and sound technologies in the era of deep learning
    Giovanni Bindi, Nils Demerlé, Rodrigo Diaz, David Genova, Aliénor Golvet, Ben Hayes, Jiawen Huang, Lele Liu, Vincent Martos, Sarah Nabi, and  others
    arXiv preprint arXiv:2310.18320, 2023
    HTML

2022

  1. ISMIR
    EnsembleSet: A new high-quality synthesised dataset for chamber ensemble separation
    Saurjya Sarkar, Emmanouil Benetos, and Mark Sandler
    In 23rd International Society for Music Information Retrieval Conference (ISMIR), 2022
    HTML

2021

  1. Interspeech
    Vocal Harmony Separation using Time-domain Neural Networks
    S Sarkar, E Benetos, and M Sandler
    In Proc. Interspeech 2021, 2021
    HTML
  2. Patent
    Voice characteristic machine learning modelling
    Saurjya Sarkar, and Nidhin Balakumar Velavendan
    Oct 2021
    WO Patent WO2021216299A1
    HTML
  3. MDX2021
    Monotimbral Ensemble Separation using Permutation Invariant Training
    Saurjya Sarkar, Emmanouil Benetos, and Mark Sandler
    In Proceedings of the MDX Workshop, ISMIR 2021, Oct 2021
    HTML
  4. Patent
    Adjusting audio characteristics for augmented reality
    Saurjya Sarkar
    Jun 2021
    US Patent 11,032,662
    HTML

2020

  1. DMRN
    Choral music separation using time-domain neural networks
    S Sarkar, E Benetos, and M Sandler
    Proceedings of the DMRN, Jun 2020

2017

  1. DAFx
    Investigation of a drum controlled cross-adaptive audio effect for live performance
    S Sarkar, JD Reiss, and Ø Brandtsegg
    In 20th International Conference on Digital Audio Effects (DAFx-17)(Edinburgh, UK), Jun 2017
    HTML

2015

  1. ApJ
    UPDATED 24 \mum PERIOD–LUMINOSITY RELATION DERIVED FROM GALACTIC CEPHEIDS
    Chow-Choong Ngeow, Saurjya Sarkar, Anupam Bhardwaj, Shashi M Kanbur, and Harinder P Singh
    The Astrophysical Journal, Jun 2015
    HTML