Debottam Dutta

Selected Publications

1. WASPAA

   A Multi-Head Relevance Weighting Framework for Learning Raw Waveform Audio Representations

   Debottam Dutta, Purvi Agrawal, and Sriram Ganapathy

   In 2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) 2021

   Bib PDF

   @inproceedings{9632708,
     author = {Dutta, Debottam and Agrawal, Purvi and Ganapathy, Sriram},
     booktitle = {2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)},
     title = {A Multi-Head Relevance Weighting Framework for Learning Raw Waveform Audio Representations},
     year = {2021},
     volume = {},
     number = {},
     pages = {191-195},
     doi = {10.1109/WASPAA52581.2021.9632708},
   }

2. Interspeech

   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

   In Proc. Interspeech 2022 2022

   PDF
3. Nature Sci. Data

   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. Data Jun 2023

   Abs Bib PDF

   This paper presents the Coswara dataset, a dataset containing diverse set of respiratory sounds and rich meta-data, recorded between April-2020 and February-2022 from 2635 individuals (1819 SARS-CoV-2 negative, 674 positive, and 142 recovered subjects). The respiratory sounds contained nine sound categories associated with variants of breathing, cough and speech. The rich metadata contained demographic information associated with age, gender and geographic location, as well as the health information relating to the symptoms, pre-existing respiratory ailments, comorbidity and SARS-CoV-2 test status. Our study is the first of its kind to manually annotate the audio quality of the entire dataset (amounting to 65 hours) through manual listening. The paper summarizes the data collection procedure, demographic, symptoms and audio data information. A COVID-19 classifier based on bi-directional long short-term (BLSTM) architecture, is trained and evaluated on the different population sub-groups contained in the dataset to understand the bias/fairness of the model. This enabled the analysis of the impact of gender, geographic location, date of recording, and language proficiency on the COVID-19 detection performance.

   @article{Bhattacharya2023-ps,
     title = {Coswara: A respiratory sounds and symptoms dataset for remote
                   screening of {SARS-CoV-2} infection},
     author = {Bhattacharya, Debarpan and Sharma, Neeraj Kumar and Dutta, Debottam and Chetupalli, Srikanth Raj and Mote, Pravin and Ganapathy, Sriram and Chandrakiran, C and Nori, Sahiti and Suhail, K K and Gonuguntla, Sadhana and Alagesan, Murali},
     journal = {Sci. Data},
     volume = {10},
     number = {1},
     pages = {397},
     month = jun,
     year = {2023},
     language = {en},
   }

4. TASLP

   Speech Dereverberation With Frequency Domain Autoregressive Modeling

   Anurenjan Purushothaman,  Debottam Dutta, Rohit Kumar, and Sriram Ganapathy

   IEEE/ACM Transactions on Audio, Speech, and Language Processing Jun 2024

   Bib PDF

   @article{10261213,
     author = {Purushothaman, Anurenjan and Dutta, Debottam and Kumar, Rohit and Ganapathy, Sriram},
     journal = {IEEE/ACM Transactions on Audio, Speech, and Language Processing},
     title = {Speech Dereverberation With Frequency Domain Autoregressive Modeling},
     year = {2024},
     volume = {32},
     number = {},
     pages = {29-38},
     keywords = {Frequency-domain analysis;Reverberation;Task analysis;Convolution;Predictive models;Mirrors;Analytical models;Dereverberation;end-to-end ASR;frequency domain auto-regressive modeling;joint modeling},
     doi = {10.1109/TASLP.2023.3317570},
   }

5. Neurips

   Multi-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 Jun 2024

   Bib PDF

   @inproceedings{xu2024multisource,
     title = {Multi-Source Music Generation with Latent Diffusion},
     author = {Xu, Zhongweiyang and Dutta, Debottam and Wei, Yu-Lin and Choudhury, Romit Roy},
     booktitle = {Audio Imagination: NeurIPS 2024 Workshop AI-Driven Speech, Music, and Sound Generation},
     year = {2024},
     url = {https://openreview.net/forum?id=bxzUnfWrgk},
   }