Dongsoo Lee

is this you? claim profile

0 followers
SAMSUNG

A review of on-device fully neural end-to-end automatic speech recognition algorithms

In this paper, we review various end-to-end automatic speech recognition...
12/14/2020 ∙ by Chanwoo Kim, et al. ∙ 0 ∙ share

read it
Extremely Low Bit Transformer Quantization for On-Device Neural Machine Translation

Transformer is being widely used in Neural Machine Translation (NMT). De...
09/16/2020 ∙ by Insoo Chung, et al. ∙ 0 ∙ share

read it
FleXOR: Trainable Fractional Quantization

Quantization based on the binary codes is gaining attention because each...
09/09/2020 ∙ by Dongsoo Lee, et al. ∙ 0 ∙ share

read it
BiQGEMM: Matrix Multiplication with Lookup Table For Binary-Coding-based Quantized DNNs

The number of parameters in deep neural networks (DNNs) is rapidly incre...
05/20/2020 ∙ by Yongkweon Jeon, et al. ∙ 14 ∙ share

read it
Learning Low-Rank Approximation for CNNs

Low-rank approximation is an effective model compression technique to no...
05/24/2019 ∙ by Dongsoo Lee, et al. ∙ 0 ∙ share

read it
Structured Compression by Unstructured Pruning for Sparse Quantized Neural Networks

Model compression techniques, such as pruning and quantization, are beco...
05/24/2019 ∙ by Se Jung Kwon, et al. ∙ 0 ∙ share

read it
Network Pruning for Low-Rank Binary Indexing

Pruning is an efficient model compression technique to remove redundancy...
05/14/2019 ∙ by Dongsoo Lee, et al. ∙ 0 ∙ share

read it
DeepTwist: Learning Model Compression via Occasional Weight Distortion

Model compression has been introduced to reduce the required hardware re...
10/30/2018 ∙ by Dongsoo Lee, et al. ∙ 0 ∙ share

read it
Retraining-Based Iterative Weight Quantization for Deep Neural Networks

Model compression has gained a lot of attention due to its ability to re...
05/29/2018 ∙ by Dongsoo Lee, et al. ∙ 0 ∙ share

read it

Dongsoo Lee

Featured Co-authors

Gu-Yeon Wei

Chanwoo Kim

Byeongwook Kim

Se Jung Kwon

Sungsoo Kim

Dhananjaya Gowda

Parichay Kapoor

Abhinav Garg

Baeseong Park

Yongkweon Jeon

Jiyeon Kim

A review of on-device fully neural end-to-end automatic speech recognition algorithms

Extremely Low Bit Transformer Quantization for On-Device Neural Machine Translation

FleXOR: Trainable Fractional Quantization

BiQGEMM: Matrix Multiplication with Lookup Table For Binary-Coding-based Quantized DNNs

Learning Low-Rank Approximation for CNNs

Structured Compression by Unstructured Pruning for Sparse Quantized Neural Networks

Network Pruning for Low-Rank Binary Indexing

DeepTwist: Learning Model Compression via Occasional Weight Distortion

Retraining-Based Iterative Weight Quantization for Deep Neural Networks