Cong-Thanh Do

Researcher, Toshiba Europe Ltd.

Joined

September 2019

Names

Cong-Thanh Do (Preferred)

Emails

****@crl.toshiba.co.uk (Confirmed)

****@toshiba.eu (Confirmed)

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

Researcher

Toshiba Europe Ltd. (toshiba.eu)

2014 – Present

Advisors, Relations & Conflicts

No relations added

Expertise

Automatic speech recogntion

2007 – Present

Speech synthesis

2013 – 2014

Speaker verification

2011 – 2014

Publications

Interactive Object Grounding Using Image-Grounded Scene Graphs and Prompt Chaining
Simon Keizer, Mohan Li, Cong-Thanh Do, Youmna Farag, Svetlana Stoyanchev, Rama Doddipatla
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Multiple-hypothesis RNN-T Loss for Unsupervised Fine-tuning and Self-training of Neural Transducer
Cong-Thanh Do, Mohan Li, Rama Doddipatla
- Published: 01 Jan 2022, Last Modified: 16 May 2023
- INTERSPEECH 2022
- Readers: Everyone
Multiple-hypothesis RNN-T Loss for Unsupervised Fine-tuning and Self-training of Neural Transducer
Cong-Thanh Do, Mohan Li, Rama Doddipatla
- Published: 01 Jan 2022, Last Modified: 16 May 2023
- CoRR 2022
- Readers: Everyone
Train Your Classifier First: Cascade Neural Networks Training from Upper Layers to Lower Layers
Shucong Zhang, Cong-Thanh Do, Rama Doddipatla, Erfan Loweimi, Peter Bell, Steve Renals
- Published: 01 Jan 2021, Last Modified: 12 May 2023
- ICASSP 2021
- Readers: Everyone
Train your classifier first: Cascade Neural Networks Training from upper layers to lower layers
Shucong Zhang, Cong-Thanh Do, Rama Doddipatla, Erfan Loweimi, Peter Bell, Steve Renals
- Published: 01 Jan 2021, Last Modified: 16 May 2023
- CoRR 2021
- Readers: Everyone
Multiple-Hypothesis CTC-Based Semi-Supervised Adaptation of End-to-End Speech Recognition
Cong-Thanh Do, Rama Doddipatla, Thomas Hain
- Published: 01 Jan 2021, Last Modified: 16 May 2023
- ICASSP 2021
- Readers: Everyone
Multiple-hypothesis CTC-based semi-supervised adaptation of end-to-end speech recognition
Cong-Thanh Do, Rama Doddipatla, Thomas Hain
- Published: 01 Jan 2021, Last Modified: 16 May 2023
- CoRR 2021
- Readers: Everyone
Learning Noise Invariant Features Through Transfer Learning For Robust End-to-End Speech Recognition
Shucong Zhang, Cong-Thanh Do, Rama Doddipatla, Steve Renals
- Published: 01 Jan 2020, Last Modified: 12 May 2023
- ICASSP 2020
- Readers: Everyone
Selective Adaptation of End-to-End Speech Recognition using Hybrid CTC/Attention Architecture for Noise Robustness
Cong-Thanh Do, Shucong Zhang, Thomas Hain
- Published: 01 Jan 2020, Last Modified: 12 May 2023
- EUSIPCO 2020
- Readers: Everyone
Subband Temporal Envelope Features and Data Augmentation for End-to-end Recognition of Distant Conversational Speech
Cong-Thanh Do
- Published: 01 Jan 2019, Last Modified: 16 May 2023
- ICASSP 2019
- Readers: Everyone

View all 24 publications

Co-Authors

View all 27 co-authors