Personal information

No personal information available

Activities

Collapse all

Education and qualifications (1)

Imperial College London: London, London, GB

2018-09-30 to present
Education
Source: Self-asserted source
Pingchuan Ma

Works (13)

Medical records condensation: a roadmap towards healthcare data democratisation

2024-01-08 | Preprint
DOI: 10.21203/rs.3.rs-3781993/v1
Contributors: Anshul Thakur; Yujiang Wang; Mingzhi Dong; Pingchuan Ma; Stavros Petridis; Li Shang; Tingting Zhu; David Clifton
Source: check_circle
Crossref

Visual speech recognition for multiple languages in the wild

Nature Machine Intelligence
2022-10-24 | Journal article
DOI: 10.1038/s42256-022-00550-z
Contributors: Pingchuan Ma; Stavros Petridis; Maja Pantic
Source: check_circle
Crossref

Visual Speech Recognition for Multiple Languages in the Wild

2022-03-08 | Preprint
DOI: 10.21203/rs.3.rs-1386805/v1
Contributors: Pingchuan Ma; Petridis Stavros; Maja Pantic
Source: check_circle
Crossref

Detecting Adversarial Attacks on Audiovisual Speech Recognition

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
2021 | Conference paper
DOI: 10.1109/ICASSP39728.2021.9413661
Source: Self-asserted source
Pingchuan Ma

End-To-End Audio-Visual Speech Recognition with Conformers

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
2021 | Conference paper
DOI: 10.1109/ICASSP39728.2021.9414567
Source: Self-asserted source
Pingchuan Ma

Lip-reading with Densely Connected Temporal Convolutional Networks

2021 IEEE Winter Conference on Applications of Computer Vision (WACV)
2021 | Conference paper
DOI: 10.1109/WACV48630.2021.00290
Source: Self-asserted source
Pingchuan Ma

Towards Practical Lipreading with Distilled and Efficient Models

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
2021 | Conference paper
DOI: 10.1109/ICASSP39728.2021.9415063
Source: Self-asserted source
Pingchuan Ma

Speech-driven Facial Animations Improve Speech-in-Noise Comprehension of Humans

2021-12-19 | Preprint
DOI: 10.1101/2021.12.18.471222
Contributors: Enrico Varano; Konstantinos Vougioukas; Pingchuan Ma; Stavros Petridis; Maja Pantic; Tobias Reichenbach
Source: check_circle
Crossref

Lipreading Using Temporal Convolutional Networks

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
2020 | Conference paper
DOI: 10.1109/ICASSP40776.2020.9053841
Source: Self-asserted source
Pingchuan Ma

Towards Pose-Invariant Lip-Reading

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
2020 | Conference paper
DOI: 10.1109/ICASSP40776.2020.9054384
Source: Self-asserted source
Pingchuan Ma

Visually Guided Self Supervised Learning of Speech Representations

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
2020 | Conference paper
DOI: 10.1109/ICASSP40776.2020.9053415
Source: Self-asserted source
Pingchuan Ma

Audio-Visual Speech Recognition with a Hybrid CTC/Attention Architecture

2018 IEEE Spoken Language Technology Workshop (SLT)
2018 | Conference paper
DOI: 10.1109/SLT.2018.8639643
Source: Self-asserted source
Pingchuan Ma

End-to-End Audiovisual Speech Recognition

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
2018 | Conference paper
DOI: 10.1109/ICASSP.2018.8461326
Source: Self-asserted source
Pingchuan Ma

Peer review (1 review for 1 publication/grant)

Review activity for International journal of computer vision. (1)
How many people are using ORCID?