BibTeX records: Rohit Paturi

download as .bib file

@article{DBLP:journals/corr/abs-2604-00310,
  author       = {Anurag Kumar and
                  Raghuveer Peri and
                  Jon Burnsky and
                  Alexandru Nelus and
                  Rohit Paturi and
                  Srikanth Vishnubhotla and
                  Yanjun Qi},
  title        = {Robust Multimodal Safety via Conditional Decoding},
  journal      = {CoRR},
  volume       = {abs/2604.00310},
  year         = {2026},
  url          = {https://doi.org/10.48550/arXiv.2604.00310},
  doi          = {10.48550/ARXIV.2604.00310},
  eprinttype   = {arXiv},
  eprint       = {2604.00310},
  timestamp    = {Thu, 07 May 2026 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2604-00310.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@inproceedings{DBLP:conf/icassp/KumarPAS25,
  author       = {Anurag Kumar and
                  Rohit Paturi and
                  Amber Afshan and
                  Sundararajan Srinivasan},
  title        = {{SEAL:} Speaker Error Correction using Acoustic-conditioned Large
                  Language Models},
  booktitle    = {2025 {IEEE} International Conference on Acoustics, Speech and Signal
                  Processing, {ICASSP} 2025, Hyderabad, India, April 6-11, 2025},
  pages        = {1--5},
  publisher    = {{IEEE}},
  year         = {2025},
  url          = {https://doi.org/10.1109/ICASSP49660.2025.10890148},
  doi          = {10.1109/ICASSP49660.2025.10890148},
  timestamp    = {Wed, 02 Jul 2025 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/KumarPAS25.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/corr/abs-2501-08421,
  author       = {Anurag Kumar and
                  Rohit Paturi and
                  Amber Afshan and
                  Sundararajan Srinivasan},
  title        = {{SEAL:} Speaker Error Correction using Acoustic-conditioned Large
                  Language Models},
  journal      = {CoRR},
  volume       = {abs/2501.08421},
  year         = {2025},
  url          = {https://doi.org/10.48550/arXiv.2501.08421},
  doi          = {10.48550/ARXIV.2501.08421},
  eprinttype   = {arXiv},
  eprint       = {2501.08421},
  timestamp    = {Fri, 28 Feb 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2501-08421.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@inproceedings{DBLP:conf/interspeech/LiGPS24,
  author       = {Xiang Li and
                  Vivek Govindan and
                  Rohit Paturi and
                  Sundararajan Srinivasan},
  editor       = {Itshak Lapidot and
                  Sharon Gannot},
  title        = {Speakers Unembedded: Embedding-free Approach to Long-form Neural Diarization},
  booktitle    = {25th Annual Conference of the International Speech Communication Association,
                  Interspeech 2024, Kos, Greece, September 1-5, 2024},
  publisher    = {{ISCA}},
  year         = {2024},
  url          = {https://doi.org/10.21437/Interspeech.2024-1174},
  doi          = {10.21437/INTERSPEECH.2024-1174},
  timestamp    = {Tue, 20 May 2025 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/interspeech/LiGPS24.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@inproceedings{DBLP:conf/interspeech/PaturiLS24,
  author       = {Rohit Paturi and
                  Xiang Li and
                  Sundararajan Srinivasan},
  editor       = {Itshak Lapidot and
                  Sharon Gannot},
  title        = {{AG-LSEC:} Audio Grounded Lexical Speaker Error Correction},
  booktitle    = {25th Annual Conference of the International Speech Communication Association,
                  Interspeech 2024, Kos, Greece, September 1-5, 2024},
  publisher    = {{ISCA}},
  year         = {2024},
  url          = {https://doi.org/10.21437/Interspeech.2024-845},
  doi          = {10.21437/INTERSPEECH.2024-845},
  timestamp    = {Tue, 20 May 2025 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/interspeech/PaturiLS24.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/corr/abs-2405-08295,
  author       = {Nilaksh Das and
                  Saket Dingliwal and
                  Srikanth Ronanki and
                  Rohit Paturi and
                  Zhaocheng Huang and
                  Prashant Mathur and
                  Jie Yuan and
                  Dhanush Bekal and
                  Xing Niu and
                  Sai Muralidhar Jayanthi and
                  Xilai Li and
                  Karel Mundnich and
                  Monica Sunkara and
                  Sundararajan Srinivasan and
                  Kyu J. Han and
                  Katrin Kirchhoff},
  title        = {SpeechVerse: {A} Large-scale Generalizable Audio Language Model},
  journal      = {CoRR},
  volume       = {abs/2405.08295},
  year         = {2024},
  url          = {https://doi.org/10.48550/arXiv.2405.08295},
  doi          = {10.48550/ARXIV.2405.08295},
  eprinttype   = {arXiv},
  eprint       = {2405.08295},
  timestamp    = {Mon, 17 Jun 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2405-08295.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/corr/abs-2406-17266,
  author       = {Rohit Paturi and
                  Xiang Li and
                  Sundararajan Srinivasan},
  title        = {{AG-LSEC:} Audio Grounded Lexical Speaker Error Correction},
  journal      = {CoRR},
  volume       = {abs/2406.17266},
  year         = {2024},
  url          = {https://doi.org/10.48550/arXiv.2406.17266},
  doi          = {10.48550/ARXIV.2406.17266},
  eprinttype   = {arXiv},
  eprint       = {2406.17266},
  timestamp    = {Wed, 24 Jul 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2406-17266.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/corr/abs-2406-18679,
  author       = {Xiang Li and
                  Vivek Govindan and
                  Rohit Paturi and
                  Sundararajan Srinivasan},
  title        = {Speakers Unembedded: Embedding-free Approach to Long-form Neural Diarization},
  journal      = {CoRR},
  volume       = {abs/2406.18679},
  year         = {2024},
  url          = {https://doi.org/10.48550/arXiv.2406.18679},
  doi          = {10.48550/ARXIV.2406.18679},
  eprinttype   = {arXiv},
  eprint       = {2406.18679},
  timestamp    = {Wed, 24 Jul 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2406-18679.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@inproceedings{DBLP:conf/asru/ElluruKPBR23,
  author       = {Veera Raghavendra Elluru and
                  Devang Kulshreshtha and
                  Rohit Paturi and
                  Sravan Bodapati and
                  Srikanth Ronanki},
  title        = {Generalized Zero-Shot Audio-to-Intent Classification},
  booktitle    = {{IEEE} Automatic Speech Recognition and Understanding Workshop, {ASRU}
                  2023, Taipei, Taiwan, December 16-20, 2023},
  pages        = {1--8},
  publisher    = {{IEEE}},
  year         = {2023},
  url          = {https://doi.org/10.1109/ASRU57964.2023.10389657},
  doi          = {10.1109/ASRU57964.2023.10389657},
  timestamp    = {Tue, 13 Feb 2024 21:21:14 +0100},
  biburl       = {https://dblp.org/rec/conf/asru/ElluruKPBR23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@inproceedings{DBLP:conf/emnlp/Zuluaga-GomezHN23,
  author       = {Juan Pablo Zuluaga{-}Gomez and
                  Zhaocheng Huang and
                  Xing Niu and
                  Rohit Paturi and
                  Sundararajan Srinivasan and
                  Prashant Mathur and
                  Brian Thompson and
                  Marcello Federico},
  editor       = {Houda Bouamor and
                  Juan Pino and
                  Kalika Bali},
  title        = {End-to-End Single-Channel Speaker-Turn Aware Conversational Speech
                  Translation},
  booktitle    = {Proceedings of the 2023 Conference on Empirical Methods in Natural
                  Language Processing, {EMNLP} 2023, Singapore, December 6-10, 2023},
  pages        = {7255--7274},
  publisher    = {Association for Computational Linguistics},
  year         = {2023},
  url          = {https://doi.org/10.18653/v1/2023.emnlp-main.449},
  doi          = {10.18653/V1/2023.EMNLP-MAIN.449},
  timestamp    = {Wed, 12 Jun 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/emnlp/Zuluaga-GomezHN23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@inproceedings{DBLP:conf/interspeech/PaturiSL23,
  author       = {Rohit Paturi and
                  Sundararajan Srinivasan and
                  Xiang Li},
  editor       = {Naomi Harte and
                  Julie Carson{-}Berndsen and
                  Gareth Jones},
  title        = {Lexical Speaker Error Correction: Leveraging Language Models for Speaker
                  Diarization Error Correction},
  booktitle    = {24th Annual Conference of the International Speech Communication Association,
                  Interspeech 2023, Dublin, Ireland, August 20-24, 2023},
  pages        = {3567--3571},
  publisher    = {{ISCA}},
  year         = {2023},
  url          = {https://doi.org/10.21437/Interspeech.2023-1982},
  doi          = {10.21437/INTERSPEECH.2023-1982},
  timestamp    = {Fri, 14 Jun 2024 14:12:12 +0200},
  biburl       = {https://dblp.org/rec/conf/interspeech/PaturiSL23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/corr/abs-2306-09313,
  author       = {Rohit Paturi and
                  Sundararajan Srinivasan and
                  Xiang Li},
  title        = {Lexical Speaker Error Correction: Leveraging Language Models for Speaker
                  Diarization Error Correction},
  journal      = {CoRR},
  volume       = {abs/2306.09313},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2306.09313},
  doi          = {10.48550/ARXIV.2306.09313},
  eprinttype   = {arXiv},
  eprint       = {2306.09313},
  timestamp    = {Mon, 19 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2306-09313.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/corr/abs-2308-02160,
  author       = {Yogesh Virkar and
                  Brian Thompson and
                  Rohit Paturi and
                  Sundararajan Srinivasan and
                  Marcello Federico},
  title        = {Speaker Diarization of Scripted Audiovisual Content},
  journal      = {CoRR},
  volume       = {abs/2308.02160},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2308.02160},
  doi          = {10.48550/ARXIV.2308.02160},
  eprinttype   = {arXiv},
  eprint       = {2308.02160},
  timestamp    = {Wed, 12 Jun 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2308-02160.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/corr/abs-2311-00697,
  author       = {Juan Zuluaga{-}Gomez and
                  Zhaocheng Huang and
                  Xing Niu and
                  Rohit Paturi and
                  Sundararajan Srinivasan and
                  Prashant Mathur and
                  Brian Thompson and
                  Marcello Federico},
  title        = {End-to-End Single-Channel Speaker-Turn Aware Conversational Speech
                  Translation},
  journal      = {CoRR},
  volume       = {abs/2311.00697},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2311.00697},
  doi          = {10.48550/ARXIV.2311.00697},
  eprinttype   = {arXiv},
  eprint       = {2311.00697},
  timestamp    = {Wed, 12 Jun 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2311-00697.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/corr/abs-2311-02482,
  author       = {Veera Raghavendra Elluru and
                  Devang Kulshreshtha and
                  Rohit Paturi and
                  Sravan Bodapati and
                  Srikanth Ronanki},
  title        = {Generalized zero-shot audio-to-intent classification},
  journal      = {CoRR},
  volume       = {abs/2311.02482},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2311.02482},
  doi          = {10.48550/ARXIV.2311.02482},
  eprinttype   = {arXiv},
  eprint       = {2311.02482},
  timestamp    = {Wed, 08 Nov 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2311-02482.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@inproceedings{DBLP:conf/interspeech/PaturiSKG22,
  author       = {Rohit Paturi and
                  Sundararajan Srinivasan and
                  Katrin Kirchhoff and
                  Daniel Garcia{-}Romero},
  editor       = {Hanseok Ko and
                  John H. L. Hansen},
  title        = {Directed speech separation for automatic speech recognition of long
                  form conversational speech},
  booktitle    = {23rd Annual Conference of the International Speech Communication Association,
                  Interspeech 2022, Incheon, Korea, September 18-22, 2022},
  pages        = {5388--5392},
  publisher    = {{ISCA}},
  year         = {2022},
  url          = {https://doi.org/10.21437/Interspeech.2022-10843},
  doi          = {10.21437/INTERSPEECH.2022-10843},
  timestamp    = {Tue, 11 Jun 2024 16:45:43 +0200},
  biburl       = {https://dblp.org/rec/conf/interspeech/PaturiSKG22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/corr/abs-2112-05863,
  author       = {Rohit Paturi and
                  Sundararajan Srinivasan and
                  Katrin Kirchhoff},
  title        = {Directed Speech Separation for Automatic Speech Recognition of Long
                  Form Conversational Speech},
  journal      = {CoRR},
  volume       = {abs/2112.05863},
  year         = {2021},
  url          = {https://arxiv.org/abs/2112.05863},
  eprinttype   = {arXiv},
  eprint       = {2112.05863},
  timestamp    = {Wed, 05 Jan 2022 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2112-05863.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@inproceedings{DBLP:conf/interspeech/GuoPYLAA15,
  author       = {Jinxi Guo and
                  Rohit Paturi and
                  Gary Yeung and
                  Steven M. Lulich and
                  Harish Arsikere and
                  Abeer Alwan},
  title        = {Age-dependent height estimation and speaker normalization for children's
                  speech using the first three subglottal resonances},
  booktitle    = {16th Annual Conference of the International Speech Communication Association,
                  {INTERSPEECH} 2015, Dresden, Germany, September 6-10, 2015},
  pages        = {1665--1669},
  publisher    = {{ISCA}},
  year         = {2015},
  url          = {https://doi.org/10.21437/Interspeech.2015-384},
  doi          = {10.21437/INTERSPEECH.2015-384},
  timestamp    = {Sun, 19 Jan 2025 13:13:53 +0100},
  biburl       = {https://dblp.org/rec/conf/interspeech/GuoPYLAA15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

manage site settings

To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.