| Author | Title | Booktitle | Misc | Download |
| Ronglai Zuo, Fangyun Wei, Brian Mak | Towards Online Continuous Sign Language Recognition and Translation | Proceedings of the Conference on Empirical Methods in Natural Language Processing | November, 2024, Miami, Florida | unavailable |
| Ronglai Zuo, Brian Mak | A Simple Baseline for Spoken Language to Sign Language Translation with 3D Avatars | Proceedings of the European Conference on Computer Vision | September, 2024, Milano, Italy | DOI |
| Niu Zhe, Ronglai Zuo, Brian Mak, Fangyun Wei | A Hong Kong Sign Language Corpus Collected from Sign-interpreted TV News | Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024) | pages 636-646, May, 2024, Torino, Italy | DOI |
| Niu Zhe, Brian Mak | On the Audio-visual Synchronization for Lip-to-Speech Synthesis | Proceedings of the International Conference on Computer Vision | Oct, 2023, Paris, France | DOI |
| Ranzo Huang, Brian Mak | wav2vec 2.0 ASR for Cantonese-Speaking Older Adults in a Clinical Setting | Proceedings of Interspeech | Aug, 2023, Dublin, Ireland | DOI |
| Helen Meng, Brian Mak, Man-wai Mak, et al. | Integrated and Enhanced Pipeline System to Support Spoken Language Analytics for Screening Neurocognitive Disorders | Proceedings of Interspeech | Aug, 2023, Dublin, Ireland | DOI |
| Ronglai Zuo, Fangyun Wei, Brian Mak | Natural Language-Assisted Sign Language Recognition | Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition | June, 2023, Vancouver, Canada | DOI |
| Yutong Chen, Ronglai Zuo, Fangyun Wei, Yu Wu, Shujie Liu, Brian Mak | Two-Stream Network for Sign Language Recognition and Translation | Advances in Neural Information Processing Systems | Nov, 2022, New Orleans, USA | DOI |
| Ronglai Zuo, Brian Mak | Local Context-aware Self-attention for Continuous Sign Language Recognition | Proceedings of Interspeech | Sept, 2022, Incheon, Korea | DOI |
| Brian Mak, Raymond Chung | Synthesizing Near Native-accented Speech for a Non-native Speaker by Imitating the Pronunciation and Prosody of a Native Speaker | Proceedings of Interspeech | Sept, 2022, Incheon, Korea | DOI |
| Ronglai Zuo, Brian Mak | C2SLR: Consistency-enhanced Continuous Sign Language Recognition | Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition | June, 2022, New Orleans, Louisiana, USA | DOI |
| Raymond Chung, Brian Mak | On-the-fly Data Augmentation for Text-to-speech Style Transfer | Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop | Dec, 2021, Cartagena, Colombia | (draft) pdf |
| Jinchao Li, Jianwei Yu, Ye Zi, Simon Wong, Manwai Mak, Brian Mak, Xunying Liu, Helen Meng | A Comparative Study of Acoustic and Linguistic Features Classification for Alzheimer’s Disease Detection | Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing | June, 2021, Toronto, Canada | DOI |
| Xinyuan Yu, Brian Mak | Non-parallel Many-to-many Voice Conversion by Knowledge Transfer from a Text-to-speech Model | Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing | June, 2021, Toronto, Canada | DOI |
| Yingke Zhu, Brian Mak | Orthogonality Regularizations for End-to-End Speaker Verification | Proceedings of the Speaker and Language Recognition Workshop (Odyssey) | pages 17-23, Nov, 2020, Tokyo, Japan | DOI |
| Zhaoyu Liu, Brian Mak | Multi-lingual Multi-speaker Text-to-speech Synthesis for Voice Cloning with Online Speaker Enrollment | Proceedings of Interspeech | October, 2020, Shanghai, China | DOI |
| Niu Zhe, Brian Mak | Stochastic Fine-grained Labeling of Multi-state Sign Glosses for Continuous Sign Language Recognition | Proceedings of the European Conference on Computer Vision | August, 2020, Glasgow, United Kingdom | DOI |
| Yingke Zhu, Brian Mak | Orthogonal Training for Text-independent Speaker Verification | Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing | pages 6579-6583, May, 2020, Barcelona, Spain | DOI |
| Yingke Zhu, Tom Ko, Brian Mak | Mixup Learning Strategies for Text-independent Speaker Verification | Proceedings of Interspeech | pages 4345-4349, September, 2019, Graz, Austria | (draft) pdf |
| Hengguan Huang, Hao Wang, Brian Mak | Recurrent Poisson Process Unit for Speech Recognition | Proceedings of the AAAI Conference on Artificial Intelligence | pages 6538-6545, January, 2019, Hawaii, USA | (draft) pdf |
| Lahiru Samarakoon, Brian Mak, Albert Y.S. Lam | Domain Adaptation of End-to-end Speech Recognition in Low-resource Settings | IEEE Workshop on Spoken Language Technology | pages 382-388, December, 2018, Athens, Greece | (draft) pdf |
| Lahiru Samarakoon, Brian Mak, Albert Y.S. Lam | Subspace Based Sequence Discriminative Training of LSTM Acoustic Models with Feed-Forward Layers | Proceedings of the International Symposium of Chinese Spoken Language Processing | pages 136-140, November, 2018, Taipei, Taiwan | unavailable |
| Hengguan Huang, Brian Mak | WaveNet MH-SRU: Deep and Wide Multiple-history Simple Recurrent Unit for Speech Recognition | Proceedings of the International Symposium of Chinese Spoken Language Processing | pages 141-145, November, 2018, Taipei, Taiwan | (draft) pdf |
| Ivan Fung, Brian Mak | Multi-Head Attention for End-to-End Neural Machine Translation | Proceedings of the International Symposium of Chinese Spoken Language Processing | pages 250-254, November, 2018, Taipei, Taiwan | (draft) pdf |
| Wei Li, Brian Mak | Fast Derivation of Cross-lingual Document Vectors from Self-attentive Neural Machine Translation Model | Proceedings of Interspeech | pages 107-111, September, 2018, Hyderabad, India | (draft) pdf |
| Yingke Zhu, Tom Ko, David Snyder, Brian Mak, Daniel Povey | Self-Attentive Speaker Embeddings for Text-Independent Speaker Verification | Proceedings of Interspeech | pages 3573-3577, September, 2018, Hyderabad, India | (draft) pdf |
| Ivan Fung, Brian Mak | End-to-end low-resource lip-reading with maxout CNN and LSTM | Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing | pages 2511-2515, April, 2018, Calgary, Canada | (draft) pdf |
| Lahiru Samarakoon, Brian Mak, Khe Chai Sim | Learning Effective Factorized Hidden Layer Bases Using Student-Teacher Training for LSTM Acoustic Model Adaptation | Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing | pages 5954-5958, April, 2018, Calgary, Canada | (draft) pdf |
| Lahiru Samarakoon, Brian Mak | Unsupervised Adaptation of Student DNNs Learned from Teacher RNNs for Improved ASR Performance | Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop | pages 200-205, Dec, 2017, Okinawa, Japan | (draft) pdf |
| Lahiru Samarakoon, Brian Mak, Khe Chai Sim | Learning Factorized Transforms for Unsupervised Adaptation of LSTM-RNN Acoustic Models | Proceedings of Interspeech | pages 744-748, August, 2017, Stockholm, Sweden | (draft) pdf |
| Hengguan Huang, Brian Mak | To Improve the Robustness of LSTM-RNN Acoustic Models Using Higher-order Feedback From Multiple Histories | Proceedings of Interspeech | pages 3862-3866, August, 2017, Stockholm, Sweden | (draft) pdf |
| Wei Li, Brian Mak | Derivation of Document Vectors from Adaptation of LSTM Language Model | Proceedings of the Conference of the European Chapter of the Association for Computational Linguistics | pages 456-461, April, 2017, Valencia, Spain | (draft) pdf |
| Lahiru Samarakoon, Khe Chai Sim, Brian Mak | An Investigation Into Learning Effective Speaker Subspaces for Robust Unsupervised DNN Adaptation | Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing | pages 5035-5039, March, 2017, New Orleans, USA | DOI |
| Yingke Zhu, Brian Mak | Speeding Up Softmax Computations in DNN-based Large Vocabulary Speech Recognition by Senone Weight Vector Selection | Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing | pages 5335-5339, March, 2017, New Orleans, USA | (draft) pdf |
| Yingke Zhu, Brian Mak | An Investigation of Adaptation Techniques for Building Acoustic Models for Hearing-impaired Children in a CAPT Application | Proceedings of the International Symposium of Chinese Spoken Language Processing | November, 2016, Tianjin, China | (draft) pdf |
| Zhili Tan, Yingke Zhu, Man-Wai Mak, Brian Mak | Senone I-Vectors for Robust Speaker Verification | Proceedings of the International Symposium of Chinese Spoken Language Processing | November, 2016, Tianjin, China | (draft) pdf |
| Dongpeng Chen, Brian Mak | Distinct Triphone Acoustic Modeling Using Deep Neural Networks | Proceedings of Interspeech | pages 2645-2649, September, 2015, Dresden, Germany | (draft) pdf |
| Dongpeng Chen, Brian Mak | Joint Sequence Training of Phone and Grapheme Acoustic Model based on Multi-task Learning Deep Neural Networks | Proceedings of Interspeech | pages 1083-1086, September, 2014, Singapore | (draft) pdf |
| Tom Ko, Brian Mak, Dongpeng Chen | Modeling Inter-cluster and Intra-cluster Discrimination Among Triphones | Proceedings of the International Symposium of Chinese Spoken Language Processing | pages 103-107, September, 2014, Singapore | (draft) pdf |
| Dongpeng Chen, Brian Mak, Cheung-Chi Leung, Sunil Sivadas | Joint Acoustic Modeling of Triphones and Trigraphemes by Multi-Task Learning Deep Neural Networks for Low-Resource Speech Recognition | Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing | pages 5592-5596, May, 2014, Florence, Italy | (draft) pdf |
| Tom Ko, Brian Mak | Subspace Gaussian Mixture Model with State-dependent Subspace Dimensions | Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing | pages 1725-1729, May, 2014, Florence, Italy | (draft) pdf |
| Dongpeng Chen, Brian Mak | Distinct triphone modeling by reference model weighting | Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing | pages 7150-7153, May, 2013, Vancouver, Canada | (draft) pdf |
| Guoli Ye, Brian Mak | Speaker-Ensemble Hidden Markov Modeling For Automatic Speech Recognition | Proceedings of the International Symposium of Chinese Spoken Language Processing | Dec, 2012, HongKong | (draft) pdf |
| Guoli Ye, Brian Mak | Subspace High-density Discrete Hidden Markov Model | Proceedings of the European Signal Processing Conference | pages 1643-1647, August, 2012, Bucharest, Romania | (draft) pdf |
| Guoli Ye, Dongpeng Chen, Brian Mak | Transition Probabilities Are More Important Than We Once Thought | Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing | pages 4809-4812, March, 2012, Kyoto, Japan | (draft) pdf |
| Tom Ko, Brian Mak | Derivation of Eigentriphones By Weighted Principal Component Analysis | Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing | pages 4097-4100, March, 2012, Kyoto, Japan | (draft) pdf |
| Tom Ko, Brian Mak | A Fully Automated Derivation of State-based Eigentriphones for Triphone Modeling with No Tied States Using Regularization | Proceedings of Interspeech | pages 781-784, August, 2011, Florence, Italy | (draft) pdf |
| Tom Ko, Brian Mak | Eigentriphones: A Basis for Context-dependent Acoustic Modeling | Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing | pages 4892-4895, May, 2011, Prague, Czech Republic | (draft) pdf |
| Guoli Ye, Brian Mak | Subvector-Quantized High-density Discrete Hidden Markov Model and its Re-estimation | Proceedings of the International Symposium of Chinese Spoken Language Processing | pages 109-113, Nov, 2010, Taiwan | (draft) pdf |
| Brian Mak, Tom Ko | Problems of Modeling Phone Deletion in Conversational Speech for Speech Recognition | Proceedings of the International Symposium of Chinese Spoken Language Processing | pages 114-118, Nov, 2010, Taiwan | (draft) pdf |
| Guoli Ye, Brian Mak | The Use of Subvector Quantization and Discrete Densities for Fast GMM Computation for Speaker Verification | Proceedings of Interspeech | pages 1481-1484, Sept, 2010, Makuhari, Japan | (draft) pdf |
| Tom Ko, Brian Mak | Improving Speech Recognition by Explicit Modeling of Phone Deletions | Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing | pages 4858-4861, March, 2010, Dallas, Texas, USA | (draft) pdf |
| Guoli Ye, Brian Mak, Man Wai Mak | Fast GMM Computation for Speaker Verification Using Scalar Quantization and Discrete Densities | Proceedings of Interspeech | pages 2327-2330, Sept, 2009, Brighton, U.K. | (draft) pdf |
| Brian Mak, Tom Ko | Automatic Estimation of Decoding Parameters Using Large-Margin Iterative Linear Programming | Proceedings of Interspeech | pages 1219-1222, Sept, 2009, Brighton, U.K. | (draft) pdf |
| Brian Mak, Tom Ko | Min-max Discriminative Training of Decoding Parameters Using Iterative Linear Programming | Proceedings of Interspeech | pages 915-918, Sept, 2008, Brisbane, Australia | (draft) pdf |
| Chien-Lin Huang, Bin Ma, Chung-Hsien Wu, Brian Mak, Haizhou Li | Robust Speaker Verification Using Short-Time Frequency with Long-Time Window and Fusion of Multi-Resolutions | Proceedings of Interspeech | pages 1897-1900, Sept, 2008, Brisbane, Australia | (draft) pdf |
| Brian Mak, Benny Ng | Discriminative Training by Iterative Linear Programming Optimization | Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing | pages 4061-4064, April, 2008, Las Vegas, USA | (draft) pdf |
| Ka-Keung Wong, Man-hung Siu, Brian Mak | A Model-based Estimation of Phonotactic Language Verification Performance | Proceedings of Interspeech | pages 186-189, Aug, 2007, Antwerp, Belgium | unavailable |
| Xi Yang, Man-hung Siu, Herbert Gish, Brian Mak | Boosting with Anti-models for Automatic Language Identification | Proceedings of Interspeech | pages 342-345, Aug, 2007, Antwerp, Belgium | unavailable |
| Brian Mak, Roger Hsiao | Robustness of Several Kernel-based Fast Adaptation Methods on Noisy LVCSR | Proceedings of Interspeech | pages 266-269, Aug, 2007, Antwerp, Belgium | (draft) pdf |
| Tsz-Chung Lai, Brian Mak | Unsupervised speaker adaptation using reference speaker weighting | Proceedings of the International Symposium of Chinese Spoken Language Processing | pages 380-389, Dec 13-16, 2006, Singapore, Edited by Q. Huo and B. Ma and E-S. Chng and H. Z. Li | (draft) pdf |
| David Rossiter, Gibson Lam, Brian Mak | Automatic Audio Indexing and Audio Playback Speed Control as Tools for Language Learning | Lecture Notes in Computer Science: Advances in Web Based Learning -- ICWL 2006 | pages 290-299, 2006, Springer Berlin / Heidelberg | unavailable |
| Brian Mak, Tsz-Chung Lai, Roger Hsiao | Improving reference speaker weighting adaptation by the use of maximum-likelihood reference speakers | Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing | volume 1, pages 229-232, May 14-19, 2006, Toulouse, France | (draft) pdf |
| Ivor W. Tsang, James T. Kwok, Brian Mak, Kai Zhang, Jeffrey J. Pan | Fast Speaker Adaptation via Maximum Penalized Likelihood Kernel Regression | Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing | volume 1, pages 997-1000, May 14-19, 2006, Toulouse, France | (draft) pdf |
| Man Wai Mak, Roger Hsiao, Brian Mak | A Comparison of Various Adaptation Methods for Speaker Verification with Limited Enrollment Data | Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing | volume 1, pages 929-932, May 14-19, 2006, Toulouse, France | (draft) pdf |
| Brian Mak, S. K. Au Yeung, Y. P. Lai, M. Siu | High-density Discrete HMM with the Use of Scalar Quantization Indexing | Proceedings of Interspeech | Sept, 2005, Lisbon, Portugal | (draft) pdf |
| R. Hsiao, Brian Mak | A Comparative Study of Two Kernel Eigenspace-based Speaker Adaptation Methods on Large Vocabulary Continuous Speech Recognition | Proceedings of Interspeech | Sept, 2005, Lisbon, Portugal | (draft) pdf |
| R. Hsiao, Brian Mak | Kernel Eigenspace-based MLLR Adaptation Using Multiple Regression Classes | Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing | volume 1, pages 985-988, March 18-23, 2005, Philadelphia, USA | (draft) pdf |
| Brian Mak, S. Ho | Various Reference Speakers Determination Methods for Embedded Kernel Eigenvoice Speaker Adaptation | Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing | volume 1, pages 981-984, March 18-23, 2005, Philadelphia, USA | (draft) pdf |
| C. W. Yip, H. K. Lo, Brian Mak | Passenger Route Guidance for Multi-modal Networks | Proceedings of the International Conference on Application of Information and Communication Technology in Transport Systems in Developing Countries | August, 2004, Sri Lanka | unavailable |
| Brian Mak, R. Hsiao | Improving Eigenspace-based MLLR Adaptation by Kernel PCA | Proceedings of Interspeech | volume I, pages 13-16, October 14-18, 2004, Jeju Island, South Korea | (draft) pdf |
| Brian Mak, S. Ho, J. T. Kwok | Speedup of Kernel Eigenvoice Speaker Adaptation by Embedded Kernel PCA | Proceedings of Interspeech | volume IV, pages 2913-2916, October 14-18, 2004, Jeju Island, South Korea | (draft) pdf |
| R. Hsiao, Brian Mak | Discriminative Feature Transformation By Guided Discriminative Training | Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing | volume I, pages 897-900, May, 2004, Montreal, Canada | (draft) pdf |
| Brian Mak, J. T. Kwok, S. Ho | A Study of Various Composite Kernels for Kernel Eigenvoice Speaker Adaptation | Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing | volume I, pages 325-328, May, 2004, Montreal, Canada | (draft) pdf |
| J. T. Kwok, Brian Mak, S. Ho | Eigenvoice Speaker Adaptation via Composite Kernel PCA | Advances in Neural Information Processing Systems | 2004, Cambridge, MA, MIT Press, Edited by Thrun, S. and Saul, L. and Scholkopf, B. | (draft) pdf |
| S. Ho, Brian Mak | Joint Estimation of Thresholds in a Bi-threshold Verification Problem | Proceedings of Interspeech | pages 893-896, September, 2003, Geneva, Switzerland | (draft) pdf |
| Brian Mak, K. W. Chan | Pruning Transitions in a Hidden Markov Model with Optimal Brain Surgeon | Proceedings of Interspeech | pages 2521-2524, September, 2003, Geneva, Switzerland | (draft) pdf |
| Brian Mak, M. H. Siu, M. Ng, Y. C. Tam, Y. C. Chan, K. W. Chan, K. Y. Leung, S. Ho, F. H. Chong, J. Wong, J. Lo | PLASER: Pronunciation Learning via Automatic Speech Recognition | Proceedings of HLT-NAACL | May, 2003, Edmonton, Canada | (draft) pdf |
| Brian Mak, Y. C. Tam | Discriminative Training of Auditory Filters of Different Shapes for Robust Speech Recognition | Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing | volume 2, pages 45-48, April, 2003, HongKong | (draft) pdf |
| Brian Mak, Y. C. Tam | Performance of Discriminatively Trained Auditory Features on Aurora2 and Aurora3 | Proceedings of Interspeech | volume 1, pages 33-36, September, 2002, Denver, Colorado, USA | (draft) pdf |
| K. W. Gan, C. Y. Wang, Brian Mak | Knowledge-based Sense Pruning using the HowNet: An Alternative to Word Sense Disambiguation | Proceedings of the International Symposium of Chinese Spoken Language Processing | pages 189-192, August, 2002, Taiwan | (draft) pdf |
| Brian Mak, Y. C. Tam, Q. Li | Discriminative Auditory Features for Robust Speech Recognition | Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing | volume 1, pages 381-384, May, 2002, Orlando, Florida, USA | (draft) pdf |
| Y. C. Tam, Brian Mak | An Alternative Approach of Finding Competing Hypotheses for Better Minimum Classification Error Training | Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing | volume 1, pages 101-104, May, 2002, Orlando, Florida, USA | (draft) pdf |
| Y. C. Tam, Brian Mak | Development of an Asynchronous Multi-band System for Continuous Speech Recognition | Proceedings of Interspeech | volume 1, pages 575-578, September, 2001, Aalborg, Denmark | (draft) pdf |
| K. M. Wong, Brian Mak | Rapid Speaker Adaptation Using MLLR and Subspace Regression Classes | Proceedings of Interspeech | volume 2, pages 1253-1256, September, 2001, Aalborg, Denmark | (draft) pdf |
| Y. C. Chan, M. Siu, Brian Mak | Pruning of State-Tying Tree using Bayesian Information Criterion with Multiple Mixtures | Proceedings of Interspeech | volume IV, pages 294-297, 2000, Beijing, China | (draft) pdf |
| Y. C. Tam, Brian Mak | Optimization of Sub-Band Weights Using Simulated Noisy Speech in Multi-Band Speech Recognition | Proceedings of Interspeech | volume I, pages 313-316, 2000, Beijing, China | (draft) pdf |
| Brian Mak, Y. C. Tam | Asynchrony with Re-Trained Transition Probabilities Improves Performance in Multi-Band Speech Recognition | Proceedings of Interspeech | volume IV, pages 149-152, 2000, Beijing, China | (draft) pdf |
| K. M. Wong, Brian Mak | MAP Adaptation with Subspace Regression Classes and Tying | Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing | volume 3, pages 1551-1554, 2000, Istanbul, Turkey | (draft) pdf |
| Brian Mak, E. Bocchieri | Training of Context-Dependent Subspace Distribution Clustering Hidden Markov Model | Proceedings of the International Conference on Spoken Language Processing | volume 1, pages 308-311, 1998, Sydney, Australia | (draft) pdf |
| Brian Mak, E. Bocchieri | Training of Subspace Distribution Clustering Hidden Markov Model | Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing | volume 2, pages 673-676, 1998, Seattle, Washington, USA | (draft) pdf |
| Brian Mak, E. Bocchieri, E. Barnard | Stream Derivation and Clustering Schemes for Subspace Distribution Clustering HMM | Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop | pages 339-346, 1997, Santa Barbara, California, USA | (draft) pdf |
| E. Bocchieri, Brian Mak | Subspace Distribution Clustering for Continuous Observation Density Hidden Markov Models | Proceedings of the European Conference on Speech Communication and Technology | volume 1, pages 107-110, 1997, Rhodes, Greece | (draft) pdf |
| Brian Mak | Combining ANNs to Improve Phone Recognition | Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing | volume 4, pages 3253-3256, 1997, Munich, Germany | (draft) pdf |
| Brian Mak, E. Barnard | Phone Clustering Using the Bhattacharyya Distance | Proceedings of the International Conference on Spoken Language Processing | volume 4, pages 2005-2008, 1996, Philadelphia, USA | (draft) pdf |
| R. Cole, Y. Yan, Brian Mak, M. Fanty, T. Bailey | The Contribution of Consonants Versus Vowels to Word Recognition in Fluent Speech | Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing | volume 2, pages 853-856, 1996, Atlanta, Georgia, USA | (draft) pdf |
| Tan Lee, P. C. Ching, L. W. Chan, Brian Mak | An NN Based Tone Classifier For Cantonese | International Joint Conference on Neural Networks | volume 1, pages 287-290, 1993, Japan | (draft) pdf |
| Brian Mak, J. Junqua, B. Reaves | A Robust Speech/Non-Speech Detection Algorithm Using Time and Frequency-based Features | Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing | volume 1, pages 269-272, 1992, San Francisco, California, USA | (draft) pdf |
| Brian Mak, O. Egecioglu | Communication Parameter Tests and Parallel Back Propagation Algorithms on iPSC/2 Hypercube Multiprocessor | Proceedings of the Fifth Distributed Memory Computer Conference | volume 2, pages 1353-1364, 1990, South Carolina, USA | (draft) pdf |
Brian Kan Wing MAK
Associate Professor
