Hemant Kumar Kathania

Employment

• National Institute of Technology Sikkim

Education

Education history is unavailable.

Projects & Funding

Projects & funding information is unavailable.

Publications (13)

• Addressing Dysarthric Speech Variability with Severity-Aware Fine-Tuning of Transformer-Based Wav2vec2 ASR Models
  Circuits, Systems, and Signal Processing 2026 DOI: 10.1007/s00034-026-03515-4
  +Save
• Fusion of Data Augmentation for Improved Dysarthria Severity Classification
  Journal of Signal Processing Systems 2026 DOI: 10.1007/s11265-026-01999-6
  +Save
• A study on the layer-wise transferability of self-supervised learning features for children’s speech processing tasks
  Speech Communication 2026 DOI: 10.1016/j.specom.2026.103392
  +Save
• Role of SSL models: Finetuning and feature optimization for dysarthric speech recognition and keyword spotting
  Computers and Electrical Engineering 2026 DOI: 10.1016/j.compeleceng.2025.110921
  +Save
• Do all features matter? Layer-wise feature probing of self-supervised speech models for dysarthria severity classification
  Speech Communication 2025 DOI: 10.1016/j.specom.2025.103326
  +Save
• Zero-shot KWS for children’s speech using layer-wise features from SSL models
  Pattern Recognition Letters 2025 DOI: 10.1016/j.patrec.2025.08.010
  +Save
• Can Layer-Wise SSL Features Improve Zero-Shot ASR Performance for Children’s Speech?
  IEEE Signal Processing Letters 2025 DOI: 10.1109/LSP.2025.3602636
  +Save
• ResEmoteNet: Bridging Accuracy and Loss Reduction in Facial Emotion Recognition
  IEEE Signal Processing Letters 2025 DOI: 10.1109/LSP.2024.3521321
  +Save
• Gammatone-Filterbank Based Pitch-Normalized Cepstral Coefficients for Zero-Resource Children’s ASR
  2023 DOI: 10.1007/978-3-031-48309-7_40
  +Save
• Data Augmentation Using Spectral Warping for Low Resource Children ASR
  Journal of Signal Processing Systems 2022 DOI: 10.1007/s11265-022-01820-0
  +Save