Brian Mak - RankMe

110 papers A* 7A 24C 3Misc 22Journal 22Unranked 32

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	Detecting Neurocognitive Disorders through Analyses of Topic Evolution and Cross-modal Consistency in Visual-Stimulated Narratives. CoRR Jinchao Li, Yuejiao Wang, Junan Li, Jiawen Kang, Bo Zheng, Simon Wong, Brian Mak, Helene H. Fung, Jean Woo, Man-Wai Mak, Timothy C. Y. Kwok, Vincent C. T. Mok, Xianmin Gong, Xixin Wu, Xunying Liu, Patrick C. M. Wong, Helen Meng
2025	—	`conf`	Efficient Mouth Alignment for Visual Speech Recognition. MLSP Zhe Niu, Brian Mak
2025	—	`conf`	End-to-End Optimization for Multimodal Retrieval-Augmented Generation via Reward Backpropagation. EMNLP (Findings) Zhiyuan Fan, Longfei Yun, Ming Yan, Yumeng Wang, Dadi Guo, Brian Mak, James T. Kwok, Yi R. Fung
2025	A*	`conf`	Residual Matrix Transformers: Scaling the Size of the Residual Stream. ICML Brian Mak, Jeffrey Flanigan
2025	J	`jnl`	Residual Matrix Transformers: Scaling the Size of the Residual Stream. CoRR Brian Mak, Jeffrey Flanigan
2024	—	`conf`	A Hong Kong Sign Language Corpus Collected from Sign-interpreted TV News. LREC/COLING Zhe Niu, Ronglai Zuo, Brian Mak, Fangyun Wei
2024	J	`jnl`	A Hong Kong Sign Language Corpus Collected from Sign-interpreted TV News. CoRR Zhe Niu, Ronglai Zuo, Brian Mak, Fangyun Wei
2024	—	`conf`	A Simple Baseline for Spoken Language to Sign Language Translation with 3D Avatars. ECCV (49) Ronglai Zuo, Fangyun Wei, Zenggui Chen, Brian Mak, Jiaolong Yang, Xin Tong
2024	J	`jnl`	A Simple Baseline for Spoken Language to Sign Language Translation with 3D Avatars. CoRR Ronglai Zuo, Fangyun Wei, Zenggui Chen, Brian Mak, Jiaolong Yang, Xin Tong
2024	J	`jnl`	Improving Continuous Sign Language Recognition with Consistency Constraints and Signer Removal. ACM Trans. Multim. Comput. Commun. Appl. Ronglai Zuo, Brian Mak
2024	A*	`conf`	Towards Online Continuous Sign Language Recognition and Translation. EMNLP Ronglai Zuo, Fangyun Wei, Brian Mak
2024	J	`jnl`	Towards Online Sign Language Recognition and Translation. CoRR Ronglai Zuo, Fangyun Wei, Brian Mak
2023	J	`jnl`	Bayesian Self-Attentive Speaker Embeddings for Text-Independent Speaker Verification. IEEE ACM Trans. Audio Speech Lang. Process. Yingke Zhu, Brian Mak
2023	A	`conf`	Integrated and Enhanced Pipeline System to Support Spoken Language Analytics for Screening Neurocognitive Disorders. INTERSPEECH Helen Meng, Brian Mak, Man-Wai Mak, Helene H. Fung, Xianmin Gong, Timothy C. Y. Kwok, Xunying Liu, Vincent C. T. Mok, Patrick C. M. Wong, Jean Woo, Xixin Wu, Ka Ho Wong, Sean Shensheng Xu, Naijun Zheng, Ranzo Huang, Jiawen Kang, Xiaoquan Ke, Junan Li, Jinchao Li, Yi Wang
2023	A*	`conf`	Natural Language-Assisted Sign Language Recognition. CVPR Ronglai Zuo, Fangyun Wei, Brian Mak
2023	J	`jnl`	Natural Language-Assisted Sign Language Recognition. CoRR Ronglai Zuo, Fangyun Wei, Brian Mak
2023	A*	`conf`	On the Audio-visual Synchronization for Lip-to-Speech Synthesis. ICCV Zhe Niu, Brian Mak
2023	J	`jnl`	On the Audio-visual Synchronization for Lip-to-Speech Synthesis. CoRR Zhe Niu, Brian Mak
2023	A	`conf`	wav2vec 2.0 ASR for Cantonese-Speaking Older Adults in a Clinical Setting. INTERSPEECH Ranzo Huang, Brian Mak
2022	A	`conf`	Access on Demand: Real-time, Multi-modal Accessibility for the Deaf and Hard-of-Hearing based on Augmented Reality. ASSETS Roshan Mathew, Brian Mak, Wendy Dannels
2022	A*	`conf`	C CVPR Ronglai Zuo, Brian Mak
2022	J	`jnl`	Hardware-Control: Instrument control and automation package. J. Open Source Softw. Grant Giesbrecht, Ariel Amsellem, Timo Bauer, Brian Mak, Brian Wynne, Zhihao Qin, Arun Persaud
2022	J	`jnl`	Improving Continuous Sign Language Recognition with Consistency Constraints and Signer Removal. CoRR Ronglai Zuo, Brian Mak
2022	A	`conf`	Local Context-aware Self-attention for Continuous Sign Language Recognition. INTERSPEECH Ronglai Zuo, Brian Mak
2022	A	`conf`	Synthesizing Near Native-accented Speech for a Non-native Speaker by Imitating the Pronunciation and Prosody of a Native Speaker. INTERSPEECH Raymond Chung, Brian Mak
2022	A*	`conf`	Two-Stream Network for Sign Language Recognition and Translation. NeurIPS Yutong Chen, Ronglai Zuo, Fangyun Wei, Yu Wu, Shujie Liu, Brian Mak
2022	J	`jnl`	Two-Stream Network for Sign Language Recognition and Translation. CoRR Yutong Chen, Ronglai Zuo, Fangyun Wei, Yu Wu, Shujie Liu, Brian Mak
2021	Misc	`conf`	A Comparative Study of Acoustic and Linguistic Features Classification for Alzheimer's Disease Detection. ICASSP Jinchao Li, Jianwei Yu, Zi Ye, Simon Wong, Man-Wai Mak, Brian Mak, Xunying Liu, Helen Meng
2021	Misc	`conf`	Non-Parallel Many-To-Many Voice Conversion by Knowledge Transfer from a Text-To-Speech Model. ICASSP Xinyuan Yu, Brian Mak
2021	C	`conf`	On-The-Fly Data Augmentation for Text-to-Speech Style Transfer. ASRU Raymond Chung, Brian Mak
2020	A	`conf`	Multi-Lingual Multi-Speaker Text-to-Speech Synthesis for Voice Cloning with Online Speaker Enrollment. INTERSPEECH Zhaoyu Liu, Brian Mak
2020	Misc	`conf`	Orthogonal Training for Text-Independent Speaker Verification. ICASSP Yingke Zhu, Brian Mak
2020	—	`conf`	Orthogonality Regularizations for End-to-End Speaker Verification. Odyssey Yingke Zhu, Brian Mak
2020	—	`conf`	Stochastic Fine-Grained Labeling of Multi-state Sign Glosses for Continuous Sign Language Recognition. ECCV (16) Zhe Niu, Brian Mak
2020	J	`jnl`	Transformer based Multilingual document Embedding model. CoRR Wei Li, Brian Mak
2019	A	`conf`	Mixup Learning Strategies for Text-Independent Speaker Verification. INTERSPEECH Yingke Zhu, Tom Ko, Brian Mak
2019	A*	`conf`	Recurrent Poisson Process Unit for Speech Recognition. AAAI Hengguan Huang, Hao Wang, Brian Mak
2018	—	`conf`	Domain Adaptation of End-to-end Speech Recognition in Low-Resource Settings. SLT Lahiru Samarakoon, Brian Mak, Albert Y. S. Lam
2018	Misc	`conf`	End-To-End Low-Resource Lip-Reading with Maxout Cnn and Lstm. ICASSP Ivan Fung, Brian Mak
2018	A	`conf`	Fast Derivation of Cross-lingual Document Vectors from Self-attentive Neural Machine Translation Model. INTERSPEECH Wei Li, Brian Mak
2018	J	`jnl`	Fast derivation of neural network based document vectors with distance constraint and negative sampling. CoRR Wei Li, Brian Mak
2018	—	`conf`	Multi-Head Attention for End-to-End Neural Machine Translation. ISCSLP Ivan Fung, Brian Mak
2018	A	`conf`	Self-Attentive Speaker Embeddings for Text-Independent Speaker Verification. INTERSPEECH Yingke Zhu, Tom Ko, David Snyder, Brian Mak, Daniel Povey
2018	—	`conf`	Subspace Based Sequence Discriminative Training of LSTM Acoustic Models with Feed-Forward Layers. ISCSLP Lahiru Samarakoon, Brian Mak, Albert Y. S. Lam
2018	—	`conf`	WaveNet MH-SRU: Deep and Wide Multiple-history Simple Recurrent Unit for Speech Recognition. ISCSLP Hengguan Huang, Brian Mak
2018	Misc	`conf`	learning Effective Factorized Hidden Layer Bases Using Student-Teacher Training for LSTM Acoustic Model Adaptation. ICASSP Lahiru Samarakoon, Brian Mak, Khe Chai Sim
2017	Misc	`conf`	An investigation into learning effective speaker subspaces for robust unsupervised DNN adaptation. ICASSP Lahiru Samarakoon, Khe Chai Sim, Brian Mak
2017	—	`conf`	Derivation of Document Vectors from Adaptation of LSTM Language Model. EACL (2) Wei Li, Brian Mak
2017	A	`conf`	Learning Factorized Transforms for Unsupervised Adaptation of LSTM-RNN Acoustic Models. INTERSPEECH Lahiru Samarakoon, Brian Mak, Khe Chai Sim
2017	Misc	`conf`	Speeding up softmax computations in DNN-based large vocabulary speech recognition by senone weight vector selection. ICASSP Yingke Zhu, Brian Mak
2017	A	`conf`	To Improve the Robustness of LSTM-RNN Acoustic Models Using Higher-Order Feedback from Multiple Histories. INTERSPEECH Hengguan Huang, Brian Mak
2017	C	`conf`	Unsupervised adaptation of student DNNS learned from teacher RNNS for improved ASR performance. ASRU Lahiru Samarakoon, Brian Mak
2016	—	`conf`	An investigation of adaptation techniques for building acoustic models for hearing-impaired children in a CAPT application. ISCSLP Yingke Zhu, Brian Mak
2015	A	`conf`	Distinct triphone acoustic modeling using deep neural networks. INTERSPEECH Dongpeng Chen, Brian Mak
2015	C	`conf`	The harp of light: a musical string projection mapping. Advances in Computer Entertainment Goh Wen Shyan, Brian Mak, Chee-Onn Wong, Tan Yee Lyn, Tey Zi Ming
2014	Misc	`conf`	Joint acoustic modeling of triphones and trigraphemes by multi-task learning deep neural networks for low-resource speech recognition. ICASSP Dongpeng Chen, Brian Mak, Cheung-Chi Leung, Sunil Sivadas
2014	A	`conf`	Joint sequence training of phone and grapheme acoustic model based on multi-task learning deep neural networks. INTERSPEECH Dongpeng Chen, Brian Mak, Sunil Sivadas
2014	Misc	`conf`	Subspace Gaussian mixture model with state-dependent subspace dimensions. ICASSP Tom Ko, Brian Mak, Cheung-Chi Leung
2013	Misc	`conf`	Distinct triphone modeling by reference model weighting. ICASSP Dongpeng Chen, Brian Mak
2013	J	`jnl`	Eigentriphones for Context-Dependent Acoustic Modeling. IEEE Trans. Speech Audio Process. Tom Ko, Brian Mak
2012	Misc	`conf`	Derivation of eigentriphones by weighted principal component analysis. ICASSP Tom Ko, Brian Mak
2012	—	`conf`	Speaker-ensemble hidden Markov modeling for automatic speech recognition. ISCSLP Guoli Ye, Brian Mak
2012	—	`conf`	Subspace high-density discrete hidden Markov model for automatic speech recognition. EUSIPCO Brian Mak, Guoli Ye
2012	Misc	`conf`	Transition probabilities are more important than we once thought. ICASSP Guoli Ye, Dongpeng Chen, Brian Mak
2012	—	`conf`	Welcome message from the technical program chairs. ISCSLP Brian Mak, Bin Ma
2011	A	`conf`	A Fully Automated Derivation of State-Based Eigentriphones for Triphone Modeling with No Tied States Using Regularization. INTERSPEECH Tom Ko, Brian Mak
2011	Misc	`conf`	Eigentriphones: A basis for context-dependent acoustic modeling. ICASSP Tom Ko, Brian Mak
2010	Misc	`conf`	Improving speech recognition by explicit modeling of phone deletions. ICASSP Tom Ko, Brian Mak
2010	—	`conf`	Problems of modeling phone deletion in conversational speech for speech recognition. ISCSLP Brian Mak, Tom Ko
2010	—	`conf`	Subvector-quantized high-density discrete hidden Markov model and its re-estimation. ISCSLP Guoli Ye, Brian Mak
2010	A	`conf`	The use of subvector quantization and discrete densities for fast GMM computation for speaker verification. INTERSPEECH Guoli Ye, Brian Mak
2009	A	`conf`	Automatic estimation of decoding parameters using large-margin iterative linear programming. INTERSPEECH Brian Mak, Tom Ko
2009	A	`conf`	Fast GMM computation for speaker verification using scalar quantization and discrete densities. INTERSPEECH Guoli Ye, Brian Mak, Man-Wai Mak
2008	Misc	`conf`	Discriminative training by iterative linear programming optimization. ICASSP Brian Mak, Benny Ng
2008	A	`conf`	Min-max discriminative training of decoding parameters using iterative linear programming. INTERSPEECH Brian Mak, Tom Ko
2008	A	`conf`	Robust speaker verification using short-time frequency with long-time window and fusion of multi-resolutions. INTERSPEECH Chien-Lin Huang, Bin Ma, Chung-Hsien Wu, Brian Mak, Haizhou Li
2007	A	`conf`	A model-based estimation of phonotactic language verification performance. INTERSPEECH Kakeung Wong, Man-Hung Siu, Brian Mak
2007	A	`conf`	Boosting with anti-models for automatic language identification. INTERSPEECH Xi Yang, Man-Hung Siu, Herbert Gish, Brian Mak
2006	—	`conf`	A Comparison of Various Adaptation Methods for Speaker Verification With Limited Enrollment Data. ICASSP (1) Man-Wai Mak, Roger Wend-Huu Hsiao, Brian Mak
2006	—	`conf`	Automatic Audio Indexing and Audio Playback Speed Control as Tools for Language Learning. ICWL David Rossiter, Gibson Lam, Brian Mak
2006	—	`conf`	Fast Speaker Adaption Via Maximum Penalized Likelihood Kernel Regression. ICASSP (1) Ivor W. Tsang, James T. Kwok, Brian Mak, Kai Zhang, Jeffrey Junfeng Pan
2006	—	`conf`	Improving Reference Speaker Weighting Adaptation by the Use of Maximum-Likelihood Reference Speakers. ICASSP (1) Brian Mak, Tsz-Chung Lai, Roger Wend-Huu Hsiao
2006	J	`jnl`	Joint Optimization of the Frequency-Domain and Time-Domain Transformations in Deriving Generalized Static and Dynamic MFCCs. IEEE Signal Process. Lett. Yiu-Pong Lai, Man-Hung Siu, Brian Mak
2006	J	`jnl`	Minimization of Utterance Verification Error Rate as a Constrained Optimization Problem. IEEE Signal Process. Lett. Man-Hung Siu, Brian Mak, Wing-Hei Au
2006	—	`conf`	Unsupervised Speaker Adaptation Using Reference Speaker Weighting. ISCSLP (Selected Papers) Tsz-Chung Lai, Brian Mak
2005	A	`conf`	High-density discrete HMM with the use of scalar quantization indexing. INTERSPEECH Brian Mak, Jeff Siu-Kei Au-Yeung, Yiu-Pong Lai, Man-Hung Siu
2005	J	`jnl`	Kernel Eigenvoice Speaker Adaptation. IEEE Trans. Speech Audio Process. Brian Mak, James Tin-Yau Kwok, Simon Ka-Lung Ho
2005	—	`conf`	Various Reference Speakers Determination Methods for Embedded Kernel Eigenvoice Speaker Adaptation. ICASSP (1) Brian Mak, Simon Ka-Lung Ho
2004	—	`conf`	A study of various composite kernels for kernel eigenvoice speaker adaptation. ICASSP (1) Brian Mak, James T. Kwok, Simon Ka-Lung Ho
2004	J	`jnl`	An Acoustic-Phonetic and a Model-Theoretic Analysis of Subspace Distribution Clustering Hidden Markov Models. Int. J. Speech Technol. Brian Mak
2004	—	`conf`	Discriminative feature transformation by guided discriminative training. ICASSP (1) Roger Hsiao, Brian Mak
2004	A	`conf`	Speedup of kernel eigenvoice speaker adaptation by embedded kernel PCA. INTERSPEECH Brian Mak, Simon Ka-Lung Ho, James T. Kwok
2003	—	`conf`	Discriminative training of auditory filters of different shapes for robust speech recognition. ICASSP (2) Brian Mak, Yik-Cheung Tam, Roger Hsiao
2003	—	`conf`	Eigenvoice Speaker Adaptation via Composite Kernel PCA. NIPS James T. Kwok, Brian Mak, Simon Ka-Lung Ho
2003	A	`conf`	Joint estimation of thresholds in a bi-threshold verification problem. INTERSPEECH Simon Ka-Lung Ho, Brian Mak
2002	J	`jnl`	A mathematical relationship between full-band and multiband mel-frequency cepstral coefficients. IEEE Signal Process. Lett. Brian Mak
2002	Misc	`conf`	An alternative approach of finding competing hypotheses for better minimum classification error training. ICASSP Yik-Cheung Tam, Brian Mak
2002	Misc	`conf`	Discriminative auditory features for robust speech recognition. ICASSP Brian Mak, Yik-Cheung Tam, Peter Qi Li
2002	—	`conf`	Knowledge-based sense pruning using the hownet: an alternative to word sense disambiguation. ISCSLP Kok-Wee Gan, Chi-Yung Wang, Brian Mak
2000	Misc	`conf`	MAP adaptation with subspace regression classes and tying. ICASSP Kwok-Man Wong, Brian Mak
1998	—	`conf`	Training of context-dependent subspace distribution clustering hidden Markov model. ICSLP Brian Mak, Enrico Bocchieri
1998	Misc	`conf`	Training of subspace distribution clustering hidden Markov model. ICASSP Brian Mak, Enrico Bocchieri
1997	Misc	`conf`	Combining ANNs to improve phone recognition. ICASSP Brian Mak
1997	—	`conf`	Subspace distribution clustering for continuous observation density hidden Markov models. EUROSPEECH Enrico Bocchieri, Brian Mak
1996	—	`conf`	Phone clustering using the bhattacharyya distance. ICSLP Brian Mak, Etienne Barnard
1996	Misc	`conf`	The contribution of consonants versus vowels to word recognition in fluent speech. ICASSP Ronald A. Cole, Yonghong Yan, Brian Mak, Mark A. Fanty, Troy Bailey
1995	J	`jnl`	Tone recognition of isolated Cantonese syllables. IEEE Trans. Speech Audio Process. Tan Lee, P. C. Ching, Lai-Wan Chan, Y. H. Cheng, Brian Mak
1994	J	`jnl`	A robust algorithm for word boundary detection in the presence of noise. IEEE Trans. Speech Audio Process. Jean-Claude Junqua, Brian Mak, Ben Reaves
1992	Misc	`conf`	A robust speech/non-speech detection algorithm using time and frequency-based features. ICASSP Brian Mak, Jean-Claude Junqua, Ben Reaves
1991	—	`conf`	A study of endpoint detection algorithms in adverse conditions: incidence on a DTW and HMM recognizer. EUROSPEECH Jean-Claude Junqua, Ben Reaves, Brian Mak