Publications

Peer-reviewed publications in international conferences, workshops, and journals.

2026

2025

[C16]
Adaptive Multi-Scale Speaker Diarization on DISPLACE 2024 Challenge Task
Authors: Ravindrakumar M. Purohit, Vijay Hothi, and Hemant A. Patil
11th International Conference on Pattern Recognition and Machine Intelligence (PReMI 2025)Dec 11, 2025 · Delhi, India
[C14]
Whisper-Based Multilingual ASR for Indic Languages
Authors: Saroj Pandit, Ravindrakumar M. Purohit, and Hemant A. Patil
11th International Conference on Pattern Recognition and Machine Intelligence (PReMI 2025)Dec 11, 2025 · Delhi, India
[C12]
BAANI: A 296M-Parameter Neural Vocoder for End-to-End Punjabi Speech Synthesis
Authors: Siddharth Kumar, Nisarg Trivedi, Ravindrakumar M. Purohit, and Hemant A. Patil
17th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2025)Oct 22, 2025 · Singapore
[C6](CORE Rank: B)
Swar: A Longformer-based GAN Vocoder for Gujarati
Authors: Ravindrakumar M. Purohit, and Hemant A. Patil
33rd European Signal Processing Conference (EUSIPCO 2025)Sep 8, 2025 · Palermo, Italy
[C9]
Swar (Hindi): A Speaker-Aware Vocoder for Low-Resource Speech Synthesis
Authors: Ravindrakumar M. Purohit, and Hemant A. Patil
29th International Conference on Asian Language Processing (IALP 2025)Aug 4, 2025 · Sarawak, Malaysia
[C8]
Vaachika: A GAN-Based Neural Vocoder for Marathi Language
Authors: Ravindrakumar M. Purohit, Siddharth Kumar, and Hemant A. Patil
29th International Conference on Asian Language Processing (IALP 2025)Aug 4, 2025 · Sarawak, Malaysia
[C7]
Whether To Pretrain Neural Vocoders or Not?: An Empirical Analysis for Indic Speech Synthesis
Authors: Ravindrakumar M. Purohit, and Hemant A. Patil
29th International Conference on Asian Language Processing (IALP 2025)Aug 4, 2025 · Sarawak, Malaysia
[J1](Q1 Journal)
FedBlocks: Federated Learning and blockchain-based Privacy-Preserved Pioneering Framework for IoT Healthcare using IPFS in Web3.0 Era
Authors: Ravindrakumar M. Purohit, Jai Prakash Verma, Rachna Jain, Ashish Kumar
Cluster Computing Journal Vol. 28, Issue 2Apr 1, 2025 · Springer

2024

[CW1]
MLADDC: Multi-Lingual Audio Deepfake Detection Corpus
Authors: Arth J. Shah, Ravindrakumar M. Purohit, Dharmendra H. Vaghera, and Hemant A. Patil
Audio Imagination: NeurIPS 2024 WorkshopDec 14, 2024 · Vancouver, Canada
[C5]
GPGAN-VC: Enhancing Voice Conversion using Gradient Penalty
Authors: Ravindrakumar M. Purohit, Dharmendra H. Vaghera, and Hemant A. Patil
16th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2024)Dec 3, 2024 · Macau, China
[C4]
GGMDDC: An Audio Deepfake Detection Multilingual Dataset
Authors: Ravindrakumar M. Purohit, Arth J. Shah, Dharmendra H. Vaghera, and Hemant A. Patil
16th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2024)Dec 3, 2024 · Macau, China
[C3]
PPHiFi-TTS: Phonetic Preserved High-Fidelity Text-to-Speech for Long-Term Speech Dependencies
Authors: Ravindrakumar M. Purohit, Dharmendra H. Vaghera, and Hemant A. Patil
16th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2024)Dec 3, 2024 · Macau, China
[C2](CORE Rank: B)
FC-HiFiGAN: Aggrandizing Faster Convergence with Batchwise Normalization for Audio Synthesis
Authors: Ravindrakumar M. Purohit, Arushi Srivastava, and Hemant A. Patil
27th International Conference on Pattern Recognition (ICPR 2024)Dec 1, 2024 · Kolkata, India
[C1]
WePaMaDM-Outlier Detection: Weighted Outlier Detection using Pattern Approaches for Mass Data Mining
Authors: Ravindrakumar M. Purohit, Jai Prakash Verma, Rachna Jain, and Madhuri Bhavsar
IEEE International Conference on Advancement in Computation & Computer Technologies (InCACCT 2023)May 2, 2024 · Chandigarh, India

2023

Publications

Adaptive Multi-Scale Speaker Diarization on DISPLACE 2024 Challenge Task #

Whisper-Based Multilingual ASR for Indic Languages #

BAANI: A 296M-Parameter Neural Vocoder for End-to-End Punjabi Speech Synthesis #

Swar: A Longformer-based GAN Vocoder for Gujarati #

Swar (Hindi): A Speaker-Aware Vocoder for Low-Resource Speech Synthesis #

Vaachika: A GAN-Based Neural Vocoder for Marathi Language #

Whether To Pretrain Neural Vocoders or Not?: An Empirical Analysis for Indic Speech Synthesis #

FedBlocks: Federated Learning and blockchain-based Privacy-Preserved Pioneering Framework for IoT Healthcare using IPFS in Web3.0 Era #

MLADDC: Multi-Lingual Audio Deepfake Detection Corpus #

GPGAN-VC: Enhancing Voice Conversion using Gradient Penalty #

GGMDDC: An Audio Deepfake Detection Multilingual Dataset #

PPHiFi-TTS: Phonetic Preserved High-Fidelity Text-to-Speech for Long-Term Speech Dependencies #

FC-HiFiGAN: Aggrandizing Faster Convergence with Batchwise Normalization for Audio Synthesis #

WePaMaDM-Outlier Detection: Weighted Outlier Detection using Pattern Approaches for Mass Data Mining #

📬 Let's Connect!

Adaptive Multi-Scale Speaker Diarization on DISPLACE 2024 Challenge Task

Whisper-Based Multilingual ASR for Indic Languages

BAANI: A 296M-Parameter Neural Vocoder for End-to-End Punjabi Speech Synthesis

Swar: A Longformer-based GAN Vocoder for Gujarati

Swar (Hindi): A Speaker-Aware Vocoder for Low-Resource Speech Synthesis

Vaachika: A GAN-Based Neural Vocoder for Marathi Language

Whether To Pretrain Neural Vocoders or Not?: An Empirical Analysis for Indic Speech Synthesis

FedBlocks: Federated Learning and blockchain-based Privacy-Preserved Pioneering Framework for IoT Healthcare using IPFS in Web3.0 Era

MLADDC: Multi-Lingual Audio Deepfake Detection Corpus

GPGAN-VC: Enhancing Voice Conversion using Gradient Penalty

GGMDDC: An Audio Deepfake Detection Multilingual Dataset

PPHiFi-TTS: Phonetic Preserved High-Fidelity Text-to-Speech for Long-Term Speech Dependencies

FC-HiFiGAN: Aggrandizing Faster Convergence with Batchwise Normalization for Audio Synthesis

WePaMaDM-Outlier Detection: Weighted Outlier Detection using Pattern Approaches for Mass Data Mining