Publications

Generative Modeling and Sampling

  1. TILT: Test-Time Reward Alignment via Distribution Tilting for Compositional Generation
    ICML WorkshopTILT: Test-Time Reward Alignment via Distribution Tilting for Compositional Generation
    Debottam Dutta, Jaehoon Hahm, Jianchong Chen, and Romit Roy Choudhury
    In ICML 2026 Workshop on Structured Probabilistic Inference & Generative Modeling (SPIGM) 2026
    PDF
  2. Steer Away From Mode Collisions: Improving Composition In Diffusion Models
    ICLRSteer Away From Mode Collisions: Improving Composition In Diffusion Models
    Debottam Dutta, Jianchong Chen, Rajalaxmi Rajagopalan, Yu-Lin Wei, and Romit Roy Choudhury
    2026
    ICLR 2026
    PDF Code Website
  3. Personalized Image Generation via Human-in-the-loop Bayesian Optimization
    ICMLPersonalized Image Generation via Human-in-the-loop Bayesian Optimization
    Rajalaxmi Rajagopalan,  Debottam Dutta, Yu-Lin Wei, and Romit Roy Choudhury
    2026
    ICML 2026
    PDF Website
  4. Learning Energy-based Variational Latent Prior for VAEs
    PreprintLearning Energy-based Variational Latent Prior for VAEs
    Debottam Dutta, Chaitanya Amballa, Zhongweiyang Xu, Yu-Lin Wei, and Romit Roy Choudhury
    2025
    PDF
  5. Multi-Source Music Generation with Latent Diffusion
    NeuripsMulti-Source Music Generation with Latent Diffusion
    Zhongweiyang Xu,  Debottam Dutta, Yu-Lin Wei, and Romit Roy Choudhury
    In Audio Imagination: NeurIPS 2024 Workshop AI-Driven Speech, Music, and Sound Generation 2024
    PDF
  6. Estimating Multi-chirp Parameters using Curvature-guided Langevin Monte Carlo
    ICASSPEstimating Multi-chirp Parameters using Curvature-guided Langevin Monte Carlo
    Sattwik Basu,  Debottam Dutta, Yu-Lin Wei, and Romit Roy Choudhury
    In ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2025
    PDF

Speech/Audio Processing and Digital Health (Earlier Work)

  1. Speech Dereverberation With Frequency Domain Autoregressive Modeling
    Anurenjan Purushothaman, Debottam Dutta, Rohit Kumar, and Sriram Ganapathy
    IEEE/ACM Transactions on Audio, Speech, and Language Processing2024
    PDF
  2. Coswara: A respiratory sounds and symptoms dataset for remote screening of SARS-CoV-2 infection
    Debarpan Bhattacharya, Neeraj Kumar Sharma, Debottam Dutta, Srikanth Raj Chetupalli, Pravin Mote, Sriram Ganapathy, C Chandrakiran, Sahiti Nori, K K Suhail, Sadhana Gonuguntla, and Murali Alagesan
    Sci. Data2023
    PDF
  3. The Second Dicova Challenge: Dataset and Performance Analysis for Diagnosis of Covid-19 Using Acoustics
    Neeraj Kumar Sharma, Srikanth Raj Chetupalli, Debarpan Bhattacharya, Debottam Dutta, Pravin Mote, and Sriram Ganapathy
    ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)2022
    PDF
  4. Analyzing the impact of SARS-CoV-2 variants on respiratory sound signals
    Debarpan Bhattacharya, Debottam Dutta, Neeraj Sharma, Srikanth Raj Chetupalli, Pravin Mote, Sriram Ganapathy, Chandrakiran C, Sahiti Nori, Suhail K K, Sadhana Gonuguntla, and Murali Alagesan
    Proc. Interspeech 20222022
    PDF
  5. Acoustic Representation Learning on Breathing and Speech Signals for COVID-19 Detection
    Debottam Dutta, Debarpan Bhattacharya, Sriram Ganapathy, Amir Hossein Poorjam, Deepak Mittal, and Maneesh Singh
    Proc. Interspeech 20222022
    PDF
  6. A Multi-Head Relevance Weighting Framework for Learning Raw Waveform Audio Representations
    Debottam Dutta, Purvi Agrawal, and Sriram Ganapathy
    2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)2021
    PDF