Jyothula Sunil Kumar
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Jyothula Sunil Kumar has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- B. Arukiran Reddy
Jawaharlal Nehru Technological University, Hyderabad
1 shared publication - Raghunadh Pasunuri
Jawaharlal Nehru Technological University, Hyderabad
1 shared publication - Sape Udaya Bhaskar
Jawaharlal Nehru Technological University, Hyderabad
1 shared publication T Jaya Chandra Prasad
Department of Electronics and Communication Engineering, Rajeev Gandhi Memorial College of Engineering and Technology, Affiliated to JNTUA, Nandyal, India
1 shared publication
Latest Publications
- Open Access
- 29 December 2025
- Published by Springer Nature in Research Square
SAREC: A Semantic- Aware Retrieval-Augmented Conformer for Multilingual Low-Resource Speech Recognition
Low-resource speech recognition remains fundamentally limited by training distribution, as neural networks cannot access linguistic knowledge beyond their training data. SAREC (Semantic-Aware Retrieval Enhanced Conformer), a novel neural architecture that augments Conformer-based acoustic encoders with dynamically retrieved phonetic exemplars during both training and inference. The key innovation is frame-level retrieval with learned cross-attention fusion, enabling phonetic-precision knowledge integration at each encoding layer. Unlike existing utterance-level retrieval approaches (SRAG), SAREC system retrieves and fuses acoustic prototypes at frame granularity, capturing phonetic patterns at multiple scales through strategic insertion at encoder layers 3, 6, 9, and 12. A learned gating mechanism dynamically weights acoustic versus exemplar information per frame, providing principled information fusion superior to simple concatenation. Evaluation on Telugu, Kannada, Tamil demonstrates consistent improvements: Telugu 18.2% WER (Word Error Rate) ( (vs. 21.4% baseline, 15.0% relative, p < 0.001, 95% CI: [17.8, 18.6]%); Kannada 20.3% (vs. 24.8%, 18.1% relative); Tamil 16.4% (vs. 19.2%, 14.6% relative). Robustness improves 12.1% at 5 dB SNR (Signal to Noise Ratio), latency remains practical (356 ms/10s audio). Ablation studies confirm frame-level superiority (15% over utterance-level, K = 5 optimal).Three mechanisms explain gains: (1) phonological disambiguation, (2) morphological integration, (3) cross-dialect generalization. Results advance low-resource ASR accessibility through systematic frame-level retrieval augmentation
- 29 December 2025
- Published by Springer Nature in Research Square
Open AccessSAREC: A Semantic- Aware Retrieval-Augmented Conformer for Multilingual Low-Resource Speech Recognition
Low-resource speech recognition remains fundamentally limited by training distribution, as neural networks cannot access linguistic knowledge beyond their training data. SAREC (Semantic-Aware Retrieval Enhanced Conformer), a novel neural architecture that augments Conformer-based acoustic encoders with dynamically retrieved phonetic exemplars during both training and inference. The key innovation is frame-level retrieval with learned cross-attention fusion, enabling phonetic-precision knowledge integration at each encoding layer. Unlike existing utterance-level retrieval approaches (SRAG), SAREC system retrieves and fuses acoustic prototypes at frame granularity, capturing phonetic patterns at multiple scales through strategic insertion at encoder layers 3, 6, 9, and 12. A learned gating mechanism dynamically weights acoustic versus exemplar information per frame, providing principled information fusion superior to simple concatenation. Evaluation on Telugu, Kannada, Tamil demonstrates consistent improvements: Telugu 18.2% WER (Word Error Rate) ( (vs. 21.4% baseline, 15.0% relative, p < 0.001, 95% CI: [17.8, 18.6]%); Kannada 20.3% (vs. 24.8%, 18.1% relative); Tamil 16.4% (vs. 19.2%, 14.6% relative). Robustness improves 12.1% at 5 dB SNR (Signal to Noise Ratio), latency remains practical (356 ms/10s audio). Ablation studies confirm frame-level superiority (15% over utterance-level, K = 5 optimal).Three mechanisms explain gains: (1) phonological disambiguation, (2) morphological integration, (3) cross-dialect generalization. Results advance low-resource ASR accessibility through systematic frame-level retrieval augmentation
- 12 June 2021
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 80 (19) , 28829-28855
Low intensity visual data improvement using DWT and LWT based regularizer
- 12 June 2021
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 80 (19) , 28829-28855
Low intensity visual data improvement using DWT and LWT based regularizer