Keywords:
- Cross-modal Alignment
- F1 score
- Intent Classification
- knowledge distillation
- multitask learning
- multitask training
- named entity recognition
- pseudo-labelling
- shallow fusion
- Speaker change detection
- speaker turn detection
- speech recognition
- Spoken Language Understanding
- streaming transducer
- Word-Confusion-Networks
- XLSR-Transducer
Publications of Shashi Kumar sorted by title
F
| Fast Streaming Transducer ASR Prototyping via Knowledge Distillation with Whisper, , , , , , , , and , Idiap-RR-10-2024 |
|
| Fast Streaming Transducer ASR Prototyping via Knowledge Distillation with Whisper, , , , , , , , and , in: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, ACL, 2024 |
|
M
| Multitask Speech Recognition and Speaker Change Detection for Unknown Number of Speakers, , , , , , , and , in: Proceedings of the 49th IEEE International Conference on Acoustics, Speech, & Signal Processing (ICASSP) 2024, 2024 |
P
| Probability-Aware Word-Confusion-Network-to-Text Alignment Approach for Intent Classification, , , , , , , and , in: Proceedings of the 49th IEEE International Conference on Acoustics, Speech, & Signal Processing (ICASSP) 2024, 2024 |
|
T
| TokenVerse: Towards Unifying Speech and NLP Tasks via Transducer-based ASR, , , , , , , , and , in: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, ACL, 2024 |
[URL] |
| TokenVerse: Unifying Speech and NLP Tasks via Transducer-based ASR, , , , , , , , and , Idiap-RR-07-2024 |
[URL] |
X
| XLSR-Transducer: Streaming ASR for Self-Supervised Pretrained Models, , , , , , , and , Idiap-RR-08-2024 |
[URL] |