publications

An up-to-date list is available on

2024

  1. Arxiv
    Domain Adaptation for Contrastive Audio-Language Models
    Soham Deshmukh, Rita Singh, and Bhiksha Raj
    arXiv preprint arXiv:2402.09585 2024
    PDF
  2. Arxiv
    PAM: Prompting Audio-Language Models for Audio Quality Assessment
    Soham Deshmukh, Dareen Alharthi, Benjamin Elizalde, Hannes Gamper, Mahmoud Al Ismail, Rita Singh, Bhiksha Raj, and Huaming Wang
    arXiv preprint arXiv:2402.00282 2024
    PDF Code

2023

  1. Arxiv
    LoFT: Local Proxy Fine-tuning For Improving Transferability Of Adversarial Attacks Against Large Language Model
    Muhammad Ahmed Shah, Roshan Sharma, Hira Dhamyal, Raphael Olivier, Ankit Shah, Dareen Alharthi, Hazim T Bukhari, Massa Baali, Soham Deshmukh, Michael Kuhlmann, Bhiksha Raj, and Rita Singh
    arXiv preprint arXiv:2310.04445 2023
    PDF
  2. ICASSP 24
    Prompting Audios Using Acoustic Properties For Emotion Representation
    Hira Dhamyal, Benjamin Elizalde, Soham Deshmukh, Huaming Wang, Bhiksha Raj, and Rita Singh
    arXiv preprint arXiv:2310.02298 2023
    PDF
  3. ICASSP 24
    Training Audio Captioning Models without Audio
    Soham Deshmukh, Benjamin Elizalde, Dimitra Emmanouilidou, Bhiksha Raj, Rita Singh, and Huaming Wang
    arXiv preprint arXiv:2309.05767 2023
    PDF Code
  4. ICASSP 24
    Natural Language Supervision for General-Purpose Audio Representations
    Benjamin Elizalde, Soham Deshmukh, and Huaming Wang
    arXiv preprint arXiv:2309.05767 2023
    PDF Code
  5. NeurIPS 23
    Pengi 🐧: An Audio Language Model for Audio Tasks
    Soham Deshmukh, Benjamin Elizalde, Rita Singh, and Huaming Wang
    arXiv preprint arXiv:2305.11834 2023
    PDF Code Slides
  6. INTERSPEECH 23
    Audio Retrieval with WavText5K and CLAP Training
    Soham Deshmukh, Benjamin Elizalde, and Huaming Wang
    In Proc. INTERSPEECH 2023
    PDF Code Slides

2022

  1. ICASSP 23
    Multi-View Learning for Speech Emotion Recognition
    Daniel Tompkins, Dimitra Emmanouilidou, Soham Deshmukh, and Benjamin Elizalde
    In International Conference on Acoustics, Speech and Signal Processing Jun 2022
    PDF
  2. ICASSP 23
    CLAP 👏: Learning Audio Concepts From Natural Language Supervision
    Benjamin Elizalde, Soham Deshmukh, Mahmoud Al Ismail, and Huaming Wang
    arXiv preprint arXiv:2206.04769 Jun 2022
    arXiv PDF Code

2021

  1. INTERSPEECH 21
    Improving weakly supervised sound event detection with self-supervised auxiliary tasks
    Soham Deshmukh, Bhiksha Raj, and Rita Singh
    Jun 2021
    arXiv PDF Code Slides
  2. ICASSP 21
    Detection of Covid-19 Through the Analysis of Vocal Fold Oscillations
    Mahmoud Al Ismail, Soham Deshmukh, and Rita Singh
    In ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Jun 2021
    arXiv PDF Poster Slides
  3. ICASSP 21
    Interpreting Glottal Flow Dynamics for Detecting Covid-19 From Voice
    Soham Deshmukh, Mahmoud Al Ismail, and Rita Singh
    In ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Jun 2021
    arXiv PDF Poster Slides

2020

  1. MS project
    Multi-Task Learning for Interpretable Weakly Labelled Sound Event Detection
    Soham Deshmukh, Bhiksha Raj, and Rita Singh
    Jun 2020
    arXiv PDF Code

2019

  1. ICIIT 2019
    Temporal and Stochastic Modelling of Attacker Behaviour
    Rahul Rade, Soham Deshmukh, Ruturaj Nene, Amey S. Wadekar, and Ajay Unny
    In Advances in Data Science Jun 2019
    PDF

2018

  1. CICT 2018
    Tackling Toxic Online Communication with Recurrent Capsule Networks
    Soham Deshmukh, and Rahul Rade
    In 2018 Conference on Information and Communication Technology (CICT) Jun 2018
    PDF