Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Minje Kim

Minje Kim

Personalized Speech Enhancement through Self-Supervised Data Augmentation and Purification


Apr 05, 2021
Aswin Sivaraman, Sunwoo Kim, Minje Kim

Figure 1 for Personalized Speech Enhancement through Self-Supervised Data Augmentation and Purification
Figure 2 for Personalized Speech Enhancement through Self-Supervised Data Augmentation and Purification
Figure 3 for Personalized Speech Enhancement through Self-Supervised Data Augmentation and Purification
* 5 pages, 3 figures, under review 
  Access Paper or Ask Questions

Self-Supervised Learning for Personalized Speech Enhancement


Apr 05, 2021
Aswin Sivaraman, Minje Kim

Figure 1 for Self-Supervised Learning for Personalized Speech Enhancement
Figure 2 for Self-Supervised Learning for Personalized Speech Enhancement
Figure 3 for Self-Supervised Learning for Personalized Speech Enhancement
Figure 4 for Self-Supervised Learning for Personalized Speech Enhancement
* 10 pages, 5 figures, under review 
  Access Paper or Ask Questions

Scalable and Efficient Neural Speech Coding


Mar 27, 2021
Kai Zhen, Jongmo Sung, Mi Suk Lee, Seungkwon Beak, Minje Kim

Figure 1 for Scalable and Efficient Neural Speech Coding
Figure 2 for Scalable and Efficient Neural Speech Coding
Figure 3 for Scalable and Efficient Neural Speech Coding
Figure 4 for Scalable and Efficient Neural Speech Coding
* in submission to IEEE/ACM Transactions on Audio, Speech, and Language Processing (IEEE/ACM TASLP) 
  Access Paper or Ask Questions

Psychoacoustic Calibration of Loss Functions for Efficient End-to-End Neural Audio Coding


Dec 31, 2020
Kai Zhen, Mi Suk Lee, Jongmo Sung, Seungkwon Beack, Minje Kim

Figure 1 for Psychoacoustic Calibration of Loss Functions for Efficient End-to-End Neural Audio Coding
Figure 2 for Psychoacoustic Calibration of Loss Functions for Efficient End-to-End Neural Audio Coding
Figure 3 for Psychoacoustic Calibration of Loss Functions for Efficient End-to-End Neural Audio Coding
Figure 4 for Psychoacoustic Calibration of Loss Functions for Efficient End-to-End Neural Audio Coding
* IEEE Signal Processing Letters, vol. 27, pp. 2159-2163, 2020 
  Access Paper or Ask Questions

Self-Supervised Learning from Contrastive Mixtures for Personalized Speech Enhancement


Nov 06, 2020
Aswin Sivaraman, Minje Kim

Figure 1 for Self-Supervised Learning from Contrastive Mixtures for Personalized Speech Enhancement
Figure 2 for Self-Supervised Learning from Contrastive Mixtures for Personalized Speech Enhancement
Figure 3 for Self-Supervised Learning from Contrastive Mixtures for Personalized Speech Enhancement
Figure 4 for Self-Supervised Learning from Contrastive Mixtures for Personalized Speech Enhancement
* 4 pages, 4 figures, submitted for NeurIPS SAS Workshop 2020 and ICASSP 2021 
  Access Paper or Ask Questions

Sparse Mixture of Local Experts for Efficient Speech Enhancement


May 16, 2020
Aswin Sivaraman, Minje Kim

Figure 1 for Sparse Mixture of Local Experts for Efficient Speech Enhancement
Figure 2 for Sparse Mixture of Local Experts for Efficient Speech Enhancement
* 5 pages, 5 figures 
  Access Paper or Ask Questions

Boosted Locality Sensitive Hashing: Discriminative Binary Codes for Source Separation


Feb 14, 2020
Sunwoo Kim, Haici Yang, Minje Kim

Figure 1 for Boosted Locality Sensitive Hashing: Discriminative Binary Codes for Source Separation
Figure 2 for Boosted Locality Sensitive Hashing: Discriminative Binary Codes for Source Separation
Figure 3 for Boosted Locality Sensitive Hashing: Discriminative Binary Codes for Source Separation
Figure 4 for Boosted Locality Sensitive Hashing: Discriminative Binary Codes for Source Separation

  Access Paper or Ask Questions

Deep Autotuner: a Pitch Correcting Network for Singing Performances


Feb 12, 2020
Sanna Wager, George Tzanetakis, Cheng-i Wang, Minje Kim

Figure 1 for Deep Autotuner: a Pitch Correcting Network for Singing Performances
Figure 2 for Deep Autotuner: a Pitch Correcting Network for Singing Performances
Figure 3 for Deep Autotuner: a Pitch Correcting Network for Singing Performances
Figure 4 for Deep Autotuner: a Pitch Correcting Network for Singing Performances
* arXiv admin note: text overlap with arXiv:1902.00956 
  Access Paper or Ask Questions

Nearest Neighbor Search-Based Bitwise Source Separation Using Discriminant Winner-Take-All Hashing


Aug 26, 2019
Sunwoo Kim, Minje Kim

Figure 1 for Nearest Neighbor Search-Based Bitwise Source Separation Using Discriminant Winner-Take-All Hashing
Figure 2 for Nearest Neighbor Search-Based Bitwise Source Separation Using Discriminant Winner-Take-All Hashing
Figure 3 for Nearest Neighbor Search-Based Bitwise Source Separation Using Discriminant Winner-Take-All Hashing
Figure 4 for Nearest Neighbor Search-Based Bitwise Source Separation Using Discriminant Winner-Take-All Hashing
* 5 pages, 5 figures 
  Access Paper or Ask Questions

Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation


Aug 23, 2019
Sunwoo Kim, Mrinmoy Maity, Minje Kim

Figure 1 for Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation
Figure 2 for Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation
* 5 pages, 1 figure, 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2019) 
  Access Paper or Ask Questions

Efficient Context Aggregation for End-to-End Speech Enhancement Using a Densely Connected Convolutional and Recurrent Network


Aug 18, 2019
Kai Zhen, Mi Suk Lee, Minje Kim

Figure 1 for Efficient Context Aggregation for End-to-End Speech Enhancement Using a Densely Connected Convolutional and Recurrent Network
Figure 2 for Efficient Context Aggregation for End-to-End Speech Enhancement Using a Densely Connected Convolutional and Recurrent Network
Figure 3 for Efficient Context Aggregation for End-to-End Speech Enhancement Using a Densely Connected Convolutional and Recurrent Network
* 5 pages 
  Access Paper or Ask Questions

Cascaded Cross-Module Residual Learning towards Lightweight End-to-End Speech Coding


Jun 18, 2019
Kai Zhen, Jongmo Sung, Mi Suk Lee, Seungkwon Beack, Minje Kim

Figure 1 for Cascaded Cross-Module Residual Learning towards Lightweight End-to-End Speech Coding
Figure 2 for Cascaded Cross-Module Residual Learning towards Lightweight End-to-End Speech Coding
Figure 3 for Cascaded Cross-Module Residual Learning towards Lightweight End-to-End Speech Coding
Figure 4 for Cascaded Cross-Module Residual Learning towards Lightweight End-to-End Speech Coding
* Accepted for publication in INTERSPEECH 2019 
  Access Paper or Ask Questions

Performance Optimization on Model Synchronization in Parallel Stochastic Gradient Descent Based SVM


May 03, 2019
Vibhatha Abeykoon, Geoffrey Fox, Minje Kim

Figure 1 for Performance Optimization on Model Synchronization in Parallel Stochastic Gradient Descent Based SVM
Figure 2 for Performance Optimization on Model Synchronization in Parallel Stochastic Gradient Descent Based SVM
Figure 3 for Performance Optimization on Model Synchronization in Parallel Stochastic Gradient Descent Based SVM
Figure 4 for Performance Optimization on Model Synchronization in Parallel Stochastic Gradient Descent Based SVM
* Paper Accepted in HPML 2019 Held in conjunction with IEEE/ACM CCGRID 2019 
  Access Paper or Ask Questions

AutoQB: AutoML for Network Quantization and Binarization on Mobile Devices


Feb 15, 2019
Qian Lou, Lantao Liu, Minje Kim, Lei Jiang

Figure 1 for AutoQB: AutoML for Network Quantization and Binarization on Mobile Devices
Figure 2 for AutoQB: AutoML for Network Quantization and Binarization on Mobile Devices
Figure 3 for AutoQB: AutoML for Network Quantization and Binarization on Mobile Devices
Figure 4 for AutoQB: AutoML for Network Quantization and Binarization on Mobile Devices
* 10 pages, 12 figures 
  Access Paper or Ask Questions

Deep Autotuner: A Data-Driven Approach to Natural-Sounding Pitch Correction for Singing Voice in Karaoke Performances


Feb 03, 2019
Sanna Wager, George Tzanetakis, Cheng-i Wang, Lijiang Guo, Aswin Sivaraman, Minje Kim

Figure 1 for Deep Autotuner: A Data-Driven Approach to Natural-Sounding Pitch Correction for Singing Voice in Karaoke Performances
Figure 2 for Deep Autotuner: A Data-Driven Approach to Natural-Sounding Pitch Correction for Singing Voice in Karaoke Performances
Figure 3 for Deep Autotuner: A Data-Driven Approach to Natural-Sounding Pitch Correction for Singing Voice in Karaoke Performances
Figure 4 for Deep Autotuner: A Data-Driven Approach to Natural-Sounding Pitch Correction for Singing Voice in Karaoke Performances

  Access Paper or Ask Questions

DeepPicar: A Low-cost Deep Neural Network-based Autonomous Car


Jul 30, 2018
Michael G. Bechtel, Elise McEllhiney, Minje Kim, Heechul Yun

Figure 1 for DeepPicar: A Low-cost Deep Neural Network-based Autonomous Car
Figure 2 for DeepPicar: A Low-cost Deep Neural Network-based Autonomous Car
Figure 3 for DeepPicar: A Low-cost Deep Neural Network-based Autonomous Car
Figure 4 for DeepPicar: A Low-cost Deep Neural Network-based Autonomous Car
* To be published as a conference paper at RTCSA 2018 
  Access Paper or Ask Questions

Collaborative Deep Learning for Speech Enhancement: A Run-Time Model Selection Method Using Autoencoders


May 29, 2017
Minje Kim

Figure 1 for Collaborative Deep Learning for Speech Enhancement: A Run-Time Model Selection Method Using Autoencoders
Figure 2 for Collaborative Deep Learning for Speech Enhancement: A Run-Time Model Selection Method Using Autoencoders
Figure 3 for Collaborative Deep Learning for Speech Enhancement: A Run-Time Model Selection Method Using Autoencoders
Figure 4 for Collaborative Deep Learning for Speech Enhancement: A Run-Time Model Selection Method Using Autoencoders
* Proc. of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 76-80, March 2017 
  Access Paper or Ask Questions

Bitwise Neural Networks


Jan 22, 2016
Minje Kim, Paris Smaragdis

Figure 1 for Bitwise Neural Networks
Figure 2 for Bitwise Neural Networks
* This paper was presented at the International Conference on Machine Learning (ICML) Workshop on Resource-Efficient Machine Learning, Lille, France, Jul. 6-11, 2015 
  Access Paper or Ask Questions

Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source Separation


Oct 01, 2015
Po-Sen Huang, Minje Kim, Mark Hasegawa-Johnson, Paris Smaragdis

Figure 1 for Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source Separation
Figure 2 for Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source Separation
Figure 3 for Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source Separation
Figure 4 for Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source Separation
* IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol.23, no.12, pp.2136-2147, Dec. 2015 
  Access Paper or Ask Questions