Brian Mak
22 papers · 2017–2025 · 10 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
π§ Keyword Pioneer π Interdisciplinary Bridge π Renaissance Researcher (5) πΊοΈ Taxonomy Completionist (15) π Conference Polyglot (10)
π
Conference Polyglot
(10)
π
Academic Marathon
(8)
π
Cross-Pollinator
(12)
π₯
Mega-Team
(20)
π
Keyword Champion
(2)
ποΈ
Keyword Collector
(108)
π
Trend Setter
π
Conference Pioneer
π
Century Club
(22)
Conferences
INTERSPEECH (10)
CVPR (2)
ECCV (2)
EMNLP (2)
AAAI (1)
COLING (1)
EACL (1)
ICCV (1)
ICML (1)
NIPS (1)
Top co-authors
Keywords
sign language recognition
(5)
speech recognition
(3)
neural network
(3)
speaker embedding
(3)
automatic speech recognition
(3)
multimodal learning
(3)
speaker verification
(3)
recurrent neural network
(3)
continuous sign language
(3)
video understanding
(3)
sign language translation
(3)
self-attention mechanism
(2)
keypoint detection
(2)
embedding learning
(2)
language model
(2)
continuous sign language recognition
(2)
data augmentation
(2)
acoustic model
(2)
long short-term memory
(2)
multi-modal learning
(2)
Papers
End-to-End Optimization for Multimodal Retrieval-Augmented Generation via Reward Backpropagation
EMNLP 2025
Residual Matrix Transformers: Scaling the Size of the Residual Stream
ICML 2025
Towards Online Continuous Sign Language Recognition and Translation
EMNLP 2024
A Simple Baseline for Spoken Language to Sign Language Translation with 3D Avatars
ECCV 2024
A Hong Kong Sign Language Corpus Collected from Sign-interpreted TV News
COLING 2024
wav2vec 2.0 ASR for Cantonese-Speaking Older Adults in a Clinical Setting
INTERSPEECH 2023
Natural Language-Assisted Sign Language Recognition
CVPR 2023
On the Audio-visual Synchronization for Lip-to-Speech Synthesis
ICCV 2023
Integrated and Enhanced Pipeline System to Support Spoken Language Analytics for Screening Neurocognitive Disorders
INTERSPEECH 2023
Local Context-aware Self-attention for Continuous Sign Language Recognition
INTERSPEECH 2022
Two-Stream Network for Sign Language Recognition and Translation
NIPS 2022
C2SLR: Consistency-Enhanced Continuous Sign Language Recognition
CVPR 2022
Synthesizing Near Native-accented Speech for a Non-native Speaker by Imitating the Pronunciation and Prosody of a Native Speaker
INTERSPEECH 2022
Multi-Lingual Multi-Speaker Text-to-Speech Synthesis for Voice Cloning with Online Speaker Enrollment
INTERSPEECH 2020
Stochastic Fine-grained Labeling of Multi-state Sign Glosses for Continuous Sign Language Recognition
ECCV 2020
Recurrent Poisson Process Unit for Speech Recognition
AAAI 2019
Mixup Learning Strategies for Text-Independent Speaker Verification
INTERSPEECH 2019
Self-Attentive Speaker Embeddings for Text-Independent Speaker Verification
INTERSPEECH 2018
Fast Derivation of Cross-lingual Document Vectors from Self-attentive Neural Machine Translation Model
INTERSPEECH 2018
To Improve the Robustness of LSTM-RNN Acoustic Models Using Higher-Order Feedback from Multiple Histories
INTERSPEECH 2017
Learning Factorized Transforms for Unsupervised Adaptation of LSTM-RNN Acoustic Models
INTERSPEECH 2017
Derivation of Document Vectors from Adaptation of LSTM Language Model
EACL 2017