Alert button
Picture for Cong-Thanh Do

Cong-Thanh Do

Alert button

Multiple-hypothesis RNN-T Loss for Unsupervised Fine-tuning and Self-training of Neural Transducer

Jul 29, 2022
Cong-Thanh Do, Mohan Li, Rama Doddipatla

Figure 1 for Multiple-hypothesis RNN-T Loss for Unsupervised Fine-tuning and Self-training of Neural Transducer
Figure 2 for Multiple-hypothesis RNN-T Loss for Unsupervised Fine-tuning and Self-training of Neural Transducer
Figure 3 for Multiple-hypothesis RNN-T Loss for Unsupervised Fine-tuning and Self-training of Neural Transducer
Figure 4 for Multiple-hypothesis RNN-T Loss for Unsupervised Fine-tuning and Self-training of Neural Transducer
Viaarxiv icon

Robust multi-sensor GLMB filter: An application to multi-target tracking with bearing-only sensors

Jun 01, 2021
Cong-Thanh Do, Tran Thien Dat Nguyen, Hoa Van Nguyen

Figure 1 for Robust multi-sensor GLMB filter: An application to multi-target tracking with bearing-only sensors
Figure 2 for Robust multi-sensor GLMB filter: An application to multi-target tracking with bearing-only sensors
Figure 3 for Robust multi-sensor GLMB filter: An application to multi-target tracking with bearing-only sensors
Figure 4 for Robust multi-sensor GLMB filter: An application to multi-target tracking with bearing-only sensors
Viaarxiv icon

Multiple-hypothesis CTC-based semi-supervised adaptation of end-to-end speech recognition

Mar 31, 2021
Cong-Thanh Do, Rama Doddipatla, Thomas Hain

Figure 1 for Multiple-hypothesis CTC-based semi-supervised adaptation of end-to-end speech recognition
Figure 2 for Multiple-hypothesis CTC-based semi-supervised adaptation of end-to-end speech recognition
Figure 3 for Multiple-hypothesis CTC-based semi-supervised adaptation of end-to-end speech recognition
Figure 4 for Multiple-hypothesis CTC-based semi-supervised adaptation of end-to-end speech recognition
Viaarxiv icon

Train your classifier first: Cascade Neural Networks Training from upper layers to lower layers

Feb 09, 2021
Shucong Zhang, Cong-Thanh Do, Rama Doddipatla, Erfan Loweimi, Peter Bell, Steve Renals

Figure 1 for Train your classifier first: Cascade Neural Networks Training from upper layers to lower layers
Figure 2 for Train your classifier first: Cascade Neural Networks Training from upper layers to lower layers
Figure 3 for Train your classifier first: Cascade Neural Networks Training from upper layers to lower layers
Figure 4 for Train your classifier first: Cascade Neural Networks Training from upper layers to lower layers
Viaarxiv icon

End-to-End Speech Recognition with High-Frame-Rate Features Extraction

Jul 12, 2019
Cong-Thanh Do

Figure 1 for End-to-End Speech Recognition with High-Frame-Rate Features Extraction
Figure 2 for End-to-End Speech Recognition with High-Frame-Rate Features Extraction
Figure 3 for End-to-End Speech Recognition with High-Frame-Rate Features Extraction
Figure 4 for End-to-End Speech Recognition with High-Frame-Rate Features Extraction
Viaarxiv icon