Saurabh Kumar

Saurabh Kumar

M.Tech. (Research) student, SPIRE Lab, IISc Bengaluru

Publications

For a complete and up-to-date list, see my Google Scholar profile.

Preprints

  1. Saurabh Kumar, D. Mohanta, and P. K. Ghosh,
    “A Training Criterion with Token-Level Tolerance to Transcription Ambiguity for Automatic Speech Recognition”,
    Submitted to ICASSP 2027, 2026.
    arXiv

Conference Proceedings

  1. S. Pulikodan, A. Singh, A. Basu, N. Desai, P. K. J, P. D. Bhat, R. Dharmaraju, R. Gupta, S. Udupa, Saurabh Kumar, S. Sharma, V. Sanka, D. Tewari, H. Dhand, A. Kamat, S. Singh, S. Vashishth, P. Talukdar, R. Acharya, and P. K. Ghosh,
    “VAANI: Capturing the Language Landscape for an Inclusive Digital India”,
    Advances in Neural Information Processing Systems (NeurIPS), Evaluations and Datasets Track, 2026. To appear.
    arXiv

  2. Saurabh Kumar, A. Singh, D. G, Amartyaveer, J. Bandekar, S. Murthy, S. Sharma, S. Badiger, S. Udupa, A. Nagireddi, S. Raghavan K M, R. Saxena, J. Nanavati, R. Nanavati, J. Sridharan, A. Mehta, A. Khuraishi K S, S. P. R. Mora, P. Venkataramakrishnan, G. Date, K. P, and P. K. Ghosh,
    “RESPIN-S1.0: A read speech corpus of 10000+ hours in dialects of nine Indian Languages”,
    Thirty-ninth Conference on Neural Information Processing Systems (NeurIPS), Datasets and Benchmarks Track, 2025.
    OpenReview

  3. Saurabh Kumar, S. Sharma, G. Deekshitha, A. Singh, Amartyaveer, S. Udupa, S. Badiger, S. Khudanpur, S. Sitaram, S. Umesh, B. Ramabhadran, B. Kingsbury, H. A. Murthy, S. S. Narayanan, H. Lakougna, and P. K. Ghosh,
    “MADASR 2.0: Multi-Lingual Multi-Dialect ASR Challenge in 8 Indian Languages”,
    Proc. IEEE ASRU, 2025, pp. 1–7.
    DOI: Link

  4. Saurabh Kumar, Amartyaveer, and P. K. Ghosh,
    “Jointly Improving Dialect Identification and ASR in Indian Languages using Multimodal Feature Fusion”,
    Proc. Interspeech 2025, 2025, pp. 2770–2774.
    DOI: Link

  5. Amartyaveer, Saurabh Kumar, S. Sharma, S. Udupa, S. Badiger, A. Singh, D. G, J. Bandekar, S. Murthy, and P. K. Ghosh,
    “Improving Dialect Identification in Indian Languages Using Multimodal Features from Dialect Informed ASR”,
    Proc. ICASSP, 2025, pp. 1–5.
    DOI: Link

  6. S. Udupa, J. Bandekar, Saurabh Kumar, D. G, S. B, A. S, S. Murthy, P. Pai, S. Raghavan, R. Nanavati, and P. K. Ghosh,
    “Adapter pre-training for improved speech recognition in unseen domains using low resource adapter tuning of self-supervised models”,
    Proc. Interspeech, 2024, pp. 2529–2533.
    DOI: Link

  7. S. Udupa, J. Bandekar, G. Deekshitha, Saurabh Kumar, P. K. Ghosh, S. Badiger, A. Singh, S. Murthy, P. Pai, S. Raghavan, and R. Nanavati,
    “Gated Multi Encoders and Multitask Objectives for Dialectal Speech Recognition in Indian Languages”,
    Proc. IEEE ASRU, 2023, pp. 1–8.
    DOI: Link

  8. A. Singh, A. Jayakumar, Deekshitha G., H. Tiwari, J. Bandekar, S. Badiger, S. Udupa, Saurabh Kumar, and P. K. Ghosh,
    “An End-to-End TTS Model in Chhattisgarhi, a Low-Resource Indian Language”,
    Speech and Computer, Cham: Springer Nature Switzerland, 2023, pp. 164–172.
    ISBN: 978-3-031-48312-7.

  9. A. Singh, A. S. Mehta, K. S. Ashish Khuraishi, G. Deekshitha, G. Date, J. Nanavati, J. Bandekar, K. Basumatary, P. Karthika, S. Badiger, S. Udupa, Saurabh Kumar, and P. K. Ghosh,
    “An ASR Corpus in Chhattisgarhi, a Low-Resource Indian Language”,
    Speech and Computer, Cham: Springer Nature Switzerland, 2023, pp. 173–181.
    ISBN: 978-3-031-48312-7.

  10. A. Bhanushali, G. Bridgman, D. G., P. Ghosh, P. Kumar, Saurabh Kumar, A. Raj Kolladath, N. Ravi, A. Seth, A. Singh, V. Sukhadia, U. S., S. Udupa, and L. V. S. V. D. Prasad,
    “Gram Vaani ASR Challenge on spontaneous telephone speech recordings in regional variations of Hindi”,
    Proc. Interspeech 2022, 2022, pp. 3548–3552.
    DOI: Link

Journal Articles

  1. S. Udupa, J. Bandekar, A. Singh, D. G, Saurabh Kumar, S. Badiger, A. Nagireddi, R. R, P. K. Ghosh, H. A. Murthy, P. Kumar, K. Tokuda, M. Hasegawa-Johnson, and P. Olbrich,
    “LIMMITS’24: Multi-Speaker, Multi-Lingual INDIC TTS With Voice Cloning”,
    IEEE Open Journal of Signal Processing, vol. 6, pp. 293–302, 2025.
    DOI: Link

  2. S. Shahnawazuddin, A. Kumar, V. Kumar, Saurabh Kumar, and W. Ahmad,
    “Robust children’s speech recognition in zero resource condition”,
    Applied Acoustics, vol. 185, p. 108382, 2022.
    DOI: Link

  3. S. Shahnawazuddin, A. Kumar, Saurabh Kumar, and W. Ahmad,
    “Enhancing robustness of zero resource children’s speech recognition system through bispectrum based front-end acoustic features”,
    Digital Signal Processing, vol. 118, p. 103226, 2021.
    DOI: Link