I try to keep it up to date; check my Google Scholar for the full list.
Published
2026
-
Vividh-ASR: A Complexity-Tiered Benchmark and Optimization Dynamics for Robust Indic Speech RecognitionInterspeech, 2026PDF arXiv
-
Windowed SummaryMixing: An Efficient Fine-Tuning of Self-Supervised Learning Models for Low-resource Speech RecognitionIEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2026PDF arXiv
-
Listen Like a Teacher: Mitigating Whisper Hallucinations using Adaptive Layer Attention and Knowledge DistillationAAAI Conference on Artificial Intelligence (Main Technical Track), 2026PDF arXiv
2025
2023
-
Bridging the Gap: Towards Linguistic Resource Development for the Low-Resource Lambani LanguageInternational Conference on Speech and Computer, 2023PDF Abstract
-
VICRA: Variance-Invariance-Covariance Regularization for Attack PredictionConference on Computer Science and Intelligence Systems, 2023PDF Abstract
-
X-ABI: Toward parameter-efficient multilingual adapter-based inference for cross-lingual transferInternational Conference on Data Management, Analytics & Innovation, 2023PDF Abstract
2021
-
Image Inpainting Applied to Art: Completing Escher’s Print GalleryJournal of LatinX in AI (LXAI) Research, 2021PDF
Under review
-
Slots Are Not Speakers: Training-Free Speaker Linking for Frozen Streaming DiarizersUnder reviewPDF arXiv
-
How Duration Modeling Shapes Punctuation in Transducer ASR: A Mechanism Study
-
MuTeR: Multi-Scale Temporal Reasoning with Boundary Proposal Guided Attention for Precise Profanity Localization