My photo

Siddharth Sigtia

Centre for Digital Music

Queen Mary University of London

Mile End Road, London, E1 4NS
Office: ENG 112

s.s.sigtia at qmul.ac.uk

About me


I am a PhD student at the Centre for Digital Music at Queen Mary University of London . I am supervised by Dr.Simon Dixon.

I am currently a researcher at the Siri Speech team at Apple. I'm working on acoustic modelling for speech recognition with neural nets.

I am interested in statistical machine learning and its application to problems in Music Information Retrieval (MIR) and speech recognition. I am particularly interested in neural networks for learning representations and recurrent neural networks for time-series modelling.

I will use this website to share my research and publications. I will also use this page to share my research code. For any questions regarding code, details of my research or anything else, feel free to contact me on the email address mentioned above.

My CV is available here.

Publications


  • Automatic Environmental Sound Recognition: Performance versus Computational Cost
    Siddharth Sigtia, Adam Stark, Sacha Krstulovic and Mark Plumbley
    IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 24, no. 11, pp. 2096-2107, Nov 2016
    IEEE Preprint
  • An End-to-End Neural Network for Polyphonic Piano Music Transcription
    Siddharth Sigtia, Emmanouil Benetos and Simon Dixon
    IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 24, no. 5, pp. 927-939, May 2016
    IEEE Preprint Supplementary Material
  • Chime-Home: A Dataset for Sound Source Recognition in a Domestic Environment
    Peter Foster, Siddharth Sigtia, Sacha Krstulovic, Jon Barker and Mark D. Plumbley
    Worshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), Oct. 2015
    Paper
  • Audio Chord Recognition with a Hybrid Recurrent Neural Network
    Siddharth Sigtia, Nicolas Boulanger-Lewandowski and Simon Dixon
    16th International Society for Music Information Retrieval Conference (ISMIR), Oct. 2015
    Paper Supplementary Material
  • A Hybrid Recurrent Neural Network for Music Transcription
    Siddharth Sigtia, Emmanouil Benetos, Nicolas Boulanger-Lewandowski, Artur S. d'Avila Garcez, Tillman Weyde and Simon Dixon
    International Conference on Acoustics, Speech, and Signal Processing (ICASSP), April 2015
    Paper Supplementary Material
  • RNN-based Music Language Models for Improving Automatic Music Transcription
    Siddharth Sigtia, Emmanouil Benetos, Srikanth Cherla, Artur S. d'Avila Garcez, Tillman Weyde and Simon Dixon
    15th International Society for Music Information Retrieval Conference (ISMIR), Oct. 2014
    Paper
  • Learning to Generate Genotypes with Neural Networks
    Alexander W. Churchill, Siddharth Sigtia and Chrisantha Fernando
    Preprint
  • A Denoising Autoencoder that Guides Stochastic Search
    Alexander W. Churchill, Siddharth Sigtia and Chrisantha Fernando
    Preprint Code
  • Improved Music Feature Learning With Deep Neural Networks
    Siddharth Sigtia and Simon Dixon
    International Conference on Acoustics, Speech, and Signal Processing (ICASSP), May 2014.
    Paper Code