Wonyong Sung

发表

Finite Wordlength Effects Evaluation of the MPEG-2 Audio Decoder

Seehyun Kim, Min-seep Jeong, Jongseo Sohn, 1996 .

Fixed-point simulation utility for C and C++ based digital signal processing programs

Seehyun Kim, Wonyong Sung, 1994, Proceedings of 1994 28th Asilomar Conference on Signals, Systems and Computers.

Accelerating Speech Recognition on Mulicore and Manycore Platforms

Kurt Keutzer, Christopher J. Hughes, Wonyong Sung, 2009 .

Compression of Deep Neural Networks with Structured Sparse Ternary Coding

Wonyong Sung, Yoonho Boo, 2018, Journal of Signal Processing Systems.

A floating-point to fixed-point assembly program translator for the TMS 320C25

Seehyun Kim, Wonyong Sung, Seehyun Kim, 1994 .

TernGEMM: GEneral Matrix Multiply Library with Ternary Weights for Fast DNN Inference

Jungwook Choi, Wonyong Sung, B. Shim, 2021, 2021 IEEE Workshop on Signal Processing Systems (SiPS).

Performance Assessment of Automatic Sleep Stage Classification Using Only Partial PSG Sensors

Wonyong Sung, Iksoo Choi, 2022, 2022 IEEE Biomedical Circuits and Systems Conference (BioCAS).

Wordlength optimization of an MPEG-2 audio decoder

Min-Seop Jeong, Seehyun Kim, Jongseo Sohn, 1996, Proceedings of APCCAS'96 - Asia Pacific Conference on Circuits and Systems.

Fixed-point feedforward deep neural network design using weights +1, 0, and −1

Kyuyeon Hwang, Wonyong Sung, Wonyong Sung, 2014, 2014 IEEE Workshop on Signal Processing Systems (SiPS).

Understanding the Role of Self Attention for Efficient Speech Recognition

Jungwook Choi, Wonyong Sung, Kyuhong Shim, 2022, International Conference on Learning Representations.

Exploring Attention Map Reuse for Efficient Transformer Neural Networks

Jungwook Choi, Wonyong Sung, Kyuhong Shim, 2023, ArXiv.

Korean Tokenization for Beam Search Rescoring in Speech Recognition

Wonyong Sung, Kyuhong Shim, Hyewon Bae, 2022, 2023 International Conference on Electronics, Information, and Communication (ICEIC).

A Comparison of Transformer, Convolutional, and Recurrent Neural Networks on Phoneme Recognition

Wonyong Sung, Kyuhong Shim, 2022, ArXiv.

Wonyong Sung, Kyuhong Shim, W. Sung, 2022, INTERSPEECH.

Parallel scalability in speech recognition

Wonyong Sung, Yen-Kuang Chen, Youngmin Yi, 2009, IEEE Signal Processing Magazine.

Teacher Intervention: Improving Convergence of Quantization Aware Training for Ultra-Low Precision Transformers

Jungwook Choi, Wonyong Sung, Seongmin Park, 2023, EACL.

Layer-wise Pruning of Transformer Attention Heads for Efficient Language Modeling

Wonyong Sung, Iksoo Choi, Kyuhong Shim, 2021, 2021 18th International SoC Design Conference (ISOCC).

Quantized Neural Networks: Characterization and Holistic Optimization

Sungho Shin, Yoonho Boo, Wonyong Sung, 2020, 2020 IEEE Workshop on Signal Processing Systems (SiPS).

Fixed-Point Optimization of Transformer Neural Network

Yoonho Boo, Wonyong Sung, Wonyong Sung, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

SQWA: Stochastic Quantized Weight Averaging For Improving The Generalization Capability Of Low-Precision Deep Neural Networks pdf

Sungho Shin, Yoonho Boo, Wonyong Sung, 2020, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Generative Knowledge Transfer for Neural Language Models

Sungho Shin, Wonyong Sung, Kyuyeon Hwang, 2016, 1608.04077.

Sleep Model - A Sequence Model for Predicting the Next Sleep Stage

Wonyong Sung, Iksoo Choi, 2023, arXiv.org.

Macro-Block Dropout for Improved Regularization in Training End-to-End Speech Recognition Models

Wonyong Sung, Chanwoo Kim, Jinhwan Park, 2022, Spoken Language Technology Workshop.

Memory access pattern-aware DRAM performance model for multi-core systems

Hyojin Choi, Jongbok Lee, Wonyong Sung, 2011, (IEEE ISPASS) IEEE INTERNATIONAL SYMPOSIUM ON PERFORMANCE ANALYSIS OF SYSTEMS AND SOFTWARE.

Memory access overhead reduction for a digital color copier implementation using a VLIW digital signal processor

Wonyong Sung, Moonseok Kang, Wonyong Sung, 2005, 2005 IEEE International Symposium on Circuits and Systems.

Implementation of an H.264 motion estimation algorithm on a VLIW programmable digital signal processor

Wonyong Sung, Hyuchang Im, Wonchul Lee, 2005, IEEE Workshop on Signal Processing Systems Design and Implementation, 2005..

EFFICIENT SPEECH RECOGNITION

Jungwook Choi, Wonyong Sung, Kyuhong Shim, 2022 .

Token-Scaled Logit Distillation for Ternary Weight Generative Language Models

Jungwook Choi, Wonyong Sung, Janghwan Lee, 2023, ArXiv.

Stochastic Precision Ensemble: Self-Knowledge Distillation for Quantized Deep Neural Networks pdf

Sungho Shin, Yoonho Boo, Jungwook Choi, 2020, AAAI.

Knowledge Distillation for Optimization of Quantized Deep Neural Networks

Sungho Shin, Yoonho Boo, Wonyong Sung, 2019, 2020 IEEE Workshop on Signal Processing Systems (SiPS).