Kumud Tripathi

22 papers A* 1A 3Misc 1Journal 13Unranked 4
YearRankTypeTitle / Venue / Authors
2026 A* conf
Listen like a Teacher: Mitigating Whisper Hallucinations Using Adaptive Layer Attention and Knowledge Distillation.
AAAI
Kumud Tripathi, Aditya Srinivas Menon, Aman Gaurav, Raj Prakash Gohil, Pankaj Wasnik
2026 J jnl
Windowed SummaryMixing: An Efficient Fine-Tuning of Self-Supervised Learning Models for Low-resource Speech Recognition.
CoRR
Aditya Srinivas Menon, Kumud Tripathi, Raj Prakash Gohil, Pankaj Wasnik
2025 A conf
Attention Is Not Always the Answer: Optimizing Voice Activity Detection with Simple Feature Fusion.
INTERSPEECH
Kumud Tripathi, Chowdam Venkata Kumar, Pankaj Wasnik
2025 J jnl
Attention Is Not Always the Answer: Optimizing Voice Activity Detection with Simple Feature Fusion.
CoRR
Kumud Tripathi, Chowdam Venkata Kumar, Pankaj Wasnik
2025 Misc conf
Enhancing Whisper's Accuracy and Speed for Indian Languages through Prompt-Tuning and Tokenization.
ICASSP
Kumud Tripathi, Raj Gothi, Pankaj Wasnik
2025 A conf
LASPA: Language Agnostic Speaker Disentanglement with Prefix-Tuned Cross-Attention.
INTERSPEECH
Aditya Srinivas Menon, Raj Prakash Gohil, Kumud Tripathi, Pankaj Wasnik
2025 J jnl
LASPA: Language Agnostic Speaker Disentanglement with Prefix-Tuned Cross-Attention.
CoRR
Aditya Srinivas Menon, Raj Prakash Gohil, Kumud Tripathi, Pankaj Wasnik
2025 J jnl
Listen Like a Teacher: Mitigating Whisper Hallucinations using Adaptive Layer Attention and Knowledge Distillation.
CoRR
Kumud Tripathi, Aditya Srinivas Menon, Aman Gaurav, Raj Prakash Gohil, Pankaj Wasnik
2024 J jnl
Enhancing Whisper's Accuracy and Speed for Indian Languages through Prompt-Tuning and Tokenization.
CoRR
Kumud Tripathi, Raj Gothi, Pankaj Wasnik
2022 J jnl
Correction to: CycleGAN-Based Speech Mode Transformation Model for Robust Multilingual ASR.
Circuits Syst. Signal Process.
Kumud Tripathi, K. Sreenivasa Rao
2022 J jnl
CycleGAN-Based Speech Mode Transformation Model for Robust Multilingual ASR.
Circuits Syst. Signal Process.
Kumud Tripathi, K. Sreenivasa Rao
2022 J jnl
VOP detection for read and conversation speech using CWT coefficients and phone boundaries.
J. Ambient Intell. Humaniz. Comput.
Kumud Tripathi, K. Sreenivasa Rao
2021 J jnl
Robust vowel region detection method for multimode speech.
Multim. Tools Appl.
Kumud Tripathi, K. Sreenivasa Rao
2020 J jnl
Multilingual and multimode phone recognition system for Indian languages.
Speech Commun.
Kumud Tripathi, Mittapalle Kiran Reddy, K. Sreenivasa Rao
2020 — conf
Multilingual speech mode classification model for Indian languages.
NCC
Kumud Tripathi, K. Sreenivasa Rao
2019 J jnl
Multilingual and Multimode Phone Recognition System for Indian Languages.
CoRR
Kumud Tripathi, Mittapalle Kiran Reddy, K. Sreenivasa Rao
2019 J jnl
VOP Detection for Read and Conversation Speech using CWT Coefficients and Phone Boundaries.
CoRR
Kumud Tripathi, K. Sreenivasa Rao
2018 A conf
Analysis of sparse representation based feature on speech mode classification.
INTERSPEECH
Kumud Tripathi, K. Sreenivasa Rao
2018 — conf
Discriminative sparse representation for speech mode classification.
ICACCI
Kumud Tripathi, K. Sreenivasa Rao
2018 J jnl
Improvement of phone recognition accuracy using speech mode classification.
Int. J. Speech Technol.
Kumud Tripathi, K. Sreenivasa Rao
2016 — conf
Sentence Based Discourse Classification for Hindi Story Text-to-Speech (TTS) System.
ICON
Kumud Tripathi, Parakrant Sarkar, K. Sreenivasa Rao
2015 — conf
Continuous dynamic Indian Sign Language gesture recognition with invariant backgrounds.
ICACCI
Kumud Tripathi, Neha Baranwal, Gora Chand Nandi