Brian Mak

2.6k total citations
115 papers, 1.6k citations indexed

About

Brian Mak is a scholar working on Artificial Intelligence, Signal Processing and Computer Vision and Pattern Recognition. According to data from OpenAlex, Brian Mak has authored 115 papers receiving a total of 1.6k indexed citations (citations by other indexed papers that have themselves been cited), including 87 papers in Artificial Intelligence, 85 papers in Signal Processing and 16 papers in Computer Vision and Pattern Recognition. Recurrent topics in Brian Mak's work include Speech and Audio Processing (78 papers), Speech Recognition and Synthesis (78 papers) and Music and Audio Processing (55 papers). Brian Mak is often cited by papers focused on Speech and Audio Processing (78 papers), Speech Recognition and Synthesis (78 papers) and Music and Audio Processing (55 papers). Brian Mak collaborates with scholars based in Hong Kong, United States and Singapore. Brian Mak's co-authors include Tom Ko, Enrico Bocchieri, Etienne Barnard, J.-C. Junqua, Roger Hsiao, James T. Kwok, David Snyder, Daniel Povey, Jean-Claude Junqua and Wilson Tam and has published in prestigious journals such as The Journal of the Acoustical Society of America, IEEE Signal Processing Letters and IEEE Transactions on Systems Man and Cybernetics - Part A Systems and Humans.

In The Last Decade

Brian Mak

110 papers receiving 1.4k citations

Peers — A (Enhanced Table)

Peers by citation overlap · career bar shows stage (early→late) cites · hero ref

Name h Career Trend Papers Cites
Brian Mak Hong Kong 19 1.1k 1.0k 261 140 130 115 1.6k
Guillaume Gravier France 19 1.3k 1.2× 1.3k 1.2× 515 2.0× 141 1.0× 50 0.4× 75 1.9k
Yasuo Ariki Japan 23 1.5k 1.3× 1.4k 1.3× 673 2.6× 192 1.4× 95 0.7× 233 2.3k
Michiel Bacchiani United States 24 1.6k 1.4× 1.1k 1.0× 142 0.5× 74 0.5× 49 0.4× 66 1.9k
Thomas Hain United Kingdom 24 2.0k 1.8× 1.4k 1.4× 236 0.9× 280 2.0× 43 0.3× 187 2.3k
John S. Garofolo United States 20 1.4k 1.3× 864 0.8× 636 2.4× 111 0.8× 43 0.3× 47 2.1k
Oliver Watts United Kingdom 16 1.1k 1.0× 722 0.7× 151 0.6× 184 1.3× 21 0.2× 64 1.4k
Timothy J. Hazen United States 26 2.0k 1.9× 1.3k 1.2× 312 1.2× 88 0.6× 48 0.4× 72 2.4k
J.-L. Gauvain France 24 2.4k 2.2× 1.7k 1.7× 367 1.4× 148 1.1× 49 0.4× 65 2.8k
Gabriel Synnaeve France 19 1.5k 1.4× 546 0.5× 708 2.7× 76 0.5× 24 0.2× 54 2.1k
Dan Ellis United States 18 1.1k 1.0× 1.3k 1.2× 623 2.4× 134 1.0× 29 0.2× 36 2.0k

Countries citing papers authored by Brian Mak

Since Specialization
Citations

This map shows the geographic impact of Brian Mak's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Brian Mak with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Brian Mak more than expected).

Fields of papers citing papers by Brian Mak

Since Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Brian Mak. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Brian Mak. The network helps show where Brian Mak may publish in the future.

Co-authorship network of co-authors of Brian Mak

This figure shows the co-authorship network connecting the top 25 collaborators of Brian Mak. A scholar is included among the top collaborators of Brian Mak based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with Brian Mak. Brian Mak is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

20 of 20 papers shown
1.
Wei, Fangyun, et al.. (2024). Towards Online Continuous Sign Language Recognition and Translation. Rare & Special e-Zone (The Hong Kong University of Science and Technology). 11050–11067. 7 indexed citations
2.
Wei, Fangyun, et al.. (2023). Natural Language-Assisted Sign Language Recognition. Rare & Special e-Zone (The Hong Kong University of Science and Technology). 14890–14900. 39 indexed citations
3.
Li, Jinchao, Jianwei Yu, Zi Ye, et al.. (2021). A Comparative Study of Acoustic and Linguistic Features Classification for Alzheimer's Disease Detection. Rare & Special e-Zone (The Hong Kong University of Science and Technology). 6423–6427. 18 indexed citations
4.
Ko, Tom, et al.. (2018). Self-Attentive Speaker Embeddings for Text-Independent Speaker Verification. Rare & Special e-Zone (The Hong Kong University of Science and Technology). 3573–3577. 149 indexed citations
5.
Mak, Brian, et al.. (2017). Speeding up softmax computations in DNN-based large vocabulary speech recognition by senone weight vector selection. Rare & Special e-Zone (The Hong Kong University of Science and Technology). 5335–5339. 2 indexed citations
6.
Mak, Brian, et al.. (2015). Distinct triphone acoustic modeling using deep neural networks. Rare & Special e-Zone (The Hong Kong University of Science and Technology). 2645–2649. 4 indexed citations
7.
Mak, Brian, et al.. (2014). Joint acoustic modeling of triphones and trigraphemes by multi-task learning deep neural networks for low-resource speech recognition. Rare & Special e-Zone (The Hong Kong University of Science and Technology). 5592–5596. 54 indexed citations
8.
Ko, Tom & Brian Mak. (2011). Eigentriphones: A basis for context-dependent acoustic modeling. Rare & Special e-Zone (The Hong Kong University of Science and Technology). 3. 4892–4895. 6 indexed citations
9.
10.
Rossiter, David G., et al.. (2006). Automatic audio indexing and audio playback speed control as tools for language learning. Lecture notes in computer science. 4181. 290–299.
11.
Mak, Brian, et al.. (2006). Various Reference Speakers Determination Methods for Embedded Kernel Eigenvoice Speaker Adaptation. Rare & Special e-Zone (The Hong Kong University of Science and Technology). 1. 981–984. 5 indexed citations
12.
Mak, Brian, et al.. (2005). Kernel eigenvoice speaker adaptation. IEEE Transactions on Speech and Audio Processing. 13(5). 984–992. 36 indexed citations
13.
Mak, Brian & Roger Hsiao. (2004). Improving eigenspace-based MLLR adaptation by kernel PCA. Rare & Special e-Zone (The Hong Kong University of Science and Technology). 13–16. 11 indexed citations
14.
Mak, Brian, et al.. (2004). Discriminative Auditory-Based Featuresfor Robust Speech Recognition. IEEE Transactions on Speech and Audio Processing. 12(1). 27–36. 22 indexed citations
15.
Kwok, James T., et al.. (2003). Eigenvoice Speaker Adaptation via Composite Kernel Principal Component Analysis. Neural Information Processing Systems. 16. 1401–1408. 2 indexed citations
16.
Kwok, James T., et al.. (2003). Eigenvoice speaker adaptation via composite kernel PCA. Rare & Special e-Zone (The Hong Kong University of Science and Technology). 16. 1401–1408. 10 indexed citations
17.
Mak, Brian, Wilson Tam, & Qi Li. (2002). Discriminative auditory features for robust speech recognition. IEEE International Conference on Acoustics Speech and Signal Processing. 1. I–381. 9 indexed citations
18.
Mak, Brian, et al.. (2001). Rapid speaker adaptation using MLLR and subspace regression classes. 1253–1256. 6 indexed citations
19.
Mak, Brian & Enrico Bocchieri. (2001). Direct training of subspace distribution clustering hidden Markov model. IEEE Transactions on Speech and Audio Processing. 9(4). 378–387. 7 indexed citations
20.
Mak, Brian & Robert W. Blanning. (1998). An empirical measure of element contribution in neural networks. IEEE Transactions on Systems Man and Cybernetics Part C (Applications and Reviews). 28(4). 561–564. 28 indexed citations

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact

Breakdown of academic impact, for papers by Guillaume Gravier Breakdown of academic impact, for papers by Yasuo Ariki Breakdown of academic impact, for papers by Michiel Bacchiani Breakdown of academic impact, for papers by Thomas Hain Breakdown of academic impact, for papers by John S. Garofolo Breakdown of academic impact, for papers by Oliver Watts Breakdown of academic impact, for papers by Timothy J. Hazen Breakdown of academic impact, for papers by J.-L. Gauvain Breakdown of academic impact, for papers by Gabriel Synnaeve Breakdown of academic impact, for papers by Dan Ellis
Rankless by CCL
2026