EZ-AR-VC: Robust Arabic Voice Anonymization with Generalization Across Dialects and Code-Switching

Injy Hamed, Arigala Adarsh, Rufael Marew, Arjun Gangwar, Atharva Kulkarni, Hanan Aldarmaki, Srinivasan Umesh

Submitted to ICASSP 2027

[code]

PIXEL-KWS: Rendered-Glyph Representations for Orthographically Robust Open-Vocabulary Keyword Spotting

Arigala Adarsh, Ramesh Gundluru, Srinivasan Umesh, Ludovick Lepauloux, Hakim Hacid

Submitted to ICASSP 2027

Cross-Lingual TTS for Indian Languages: A Benchmark and Inference-Time Duration Estimation Strategies

Arigala Adarsh*, Arjun Gangwar*, Srinivasan Umesh (* equal contribution)

Submitted to AACL-IJCNLP Workshop Multi-LLL 2026

Pixel-TTS: Image based Text Rendering for Robust Text-to-Speech

Arigala Adarsh, Arjun Gangwar, Srinivasan Umesh, Yova Kementchedjhieva

Under review 2026

[Paper]

Multilingual Multi-Speaker Unit Vocoders: A Systematic Analysis of Discrete Speech Representations

Naman Kothari, Arjun Gangwar, Adarsh Arigala, S Umesh

Interspeech 2026 Proceedings

[Code] [Paper]

Enhancing Audio Captioning with Auxiliary AudioSet Semantics

Shubham Gupta*, Adarsh Arigala*, Sri Rama Murty Kodukula (* equal contribution)

preprint 2026

[Code] [Paper]