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 Kyogu Lee

Kyogu Lee

Expressive Singing Synthesis Using Local Style Token and Dual-path Pitch Encoder



Juheon Lee , Hyeong-Seok Choi , Kyogu Lee

Figure 1 for Expressive Singing Synthesis Using Local Style Token and Dual-path Pitch Encoder
Figure 2 for Expressive Singing Synthesis Using Local Style Token and Dual-path Pitch Encoder
Figure 3 for Expressive Singing Synthesis Using Local Style Token and Dual-path Pitch Encoder
Figure 4 for Expressive Singing Synthesis Using Local Style Token and Dual-path Pitch Encoder
* 4 pages, Submitted to Interspeech 2022 
   Access Paper or Ask Questions

Representation Selective Self-distillation and wav2vec 2.0 Feature Exploration for Spoof-aware Speaker Verification



Jin Woo Lee , Eungbeom Kim , Junghyun Koo , Kyogu Lee

Figure 1 for Representation Selective Self-distillation and wav2vec 2.0 Feature Exploration for Spoof-aware Speaker Verification
Figure 2 for Representation Selective Self-distillation and wav2vec 2.0 Feature Exploration for Spoof-aware Speaker Verification
Figure 3 for Representation Selective Self-distillation and wav2vec 2.0 Feature Exploration for Spoof-aware Speaker Verification
Figure 4 for Representation Selective Self-distillation and wav2vec 2.0 Feature Exploration for Spoof-aware Speaker Verification
* Submitted to Interspeech 2022 
   Access Paper or Ask Questions

Global HRTF Interpolation via Learned Affine Transformation of Hyper-conditioned Features



Jin Woo Lee , Sungho Lee , Kyogu Lee

Figure 1 for Global HRTF Interpolation via Learned Affine Transformation of Hyper-conditioned Features
Figure 2 for Global HRTF Interpolation via Learned Affine Transformation of Hyper-conditioned Features
Figure 3 for Global HRTF Interpolation via Learned Affine Transformation of Hyper-conditioned Features
Figure 4 for Global HRTF Interpolation via Learned Affine Transformation of Hyper-conditioned Features
* Submitted to Interspeech 2022 
   Access Paper or Ask Questions

End-to-end Music Remastering System Using Self-supervised and Adversarial Training



Junghyun Koo , Seungryeol Paik , Kyogu Lee

Figure 1 for End-to-end Music Remastering System Using Self-supervised and Adversarial Training
Figure 2 for End-to-end Music Remastering System Using Self-supervised and Adversarial Training
Figure 3 for End-to-end Music Remastering System Using Self-supervised and Adversarial Training
Figure 4 for End-to-end Music Remastering System Using Self-supervised and Adversarial Training
* IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2022 
   Access Paper or Ask Questions

Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representations



Hyeong-Seok Choi , Juheon Lee , Wansoo Kim , Jie Hwan Lee , Hoon Heo , Kyogu Lee

Figure 1 for Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representations
Figure 2 for Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representations
Figure 3 for Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representations
Figure 4 for Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representations
* Neural Information Processing Systems (NeurIPS) 2021 
   Access Paper or Ask Questions

Cross-domain Semi-Supervised Audio Event Classification Using Contrastive Regularization



Donmoon Lee , Kyogu Lee

Figure 1 for Cross-domain Semi-Supervised Audio Event Classification Using Contrastive Regularization
Figure 2 for Cross-domain Semi-Supervised Audio Event Classification Using Contrastive Regularization
Figure 3 for Cross-domain Semi-Supervised Audio Event Classification Using Contrastive Regularization
Figure 4 for Cross-domain Semi-Supervised Audio Event Classification Using Contrastive Regularization
* 5 pages, 3 figures, and 2 tables. Accepted paper at IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) 2021 
   Access Paper or Ask Questions

Differentiable Artificial Reverberation



Sungho Lee , Hyeong-Seok Choi , Kyogu Lee

Figure 1 for Differentiable Artificial Reverberation
Figure 2 for Differentiable Artificial Reverberation
Figure 3 for Differentiable Artificial Reverberation
Figure 4 for Differentiable Artificial Reverberation
* Manuscript in progress 
   Access Paper or Ask Questions

Room adaptive conditioning method for sound event classification in reverberant environments



Jaejun Lee , Donmoon Lee , Hyeong-Seok Choi , Kyogu Lee

Figure 1 for Room adaptive conditioning method for sound event classification in reverberant environments
Figure 2 for Room adaptive conditioning method for sound event classification in reverberant environments
Figure 3 for Room adaptive conditioning method for sound event classification in reverberant environments
Figure 4 for Room adaptive conditioning method for sound event classification in reverberant environments
* 5 pages, 3 figures, In Proceedings of the 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 
   Access Paper or Ask Questions

Reverb Conversion of Mixed Vocal Tracks Using an End-to-end Convolutional Deep Neural Network



Junghyun Koo , Seungryeol Paik , Kyogu Lee

Figure 1 for Reverb Conversion of Mixed Vocal Tracks Using an End-to-end Convolutional Deep Neural Network
Figure 2 for Reverb Conversion of Mixed Vocal Tracks Using an End-to-end Convolutional Deep Neural Network
Figure 3 for Reverb Conversion of Mixed Vocal Tracks Using an End-to-end Convolutional Deep Neural Network
Figure 4 for Reverb Conversion of Mixed Vocal Tracks Using an End-to-end Convolutional Deep Neural Network
* To appear in ICASSP 2021 
   Access Paper or Ask Questions

Real-time Denoising and Dereverberation with Tiny Recurrent U-Net



Hyeong-Seok Choi , Sungjin Park , Jie Hwan Lee , Hoon Heo , Dongsuk Jeon , Kyogu Lee

Figure 1 for Real-time Denoising and Dereverberation with Tiny Recurrent U-Net
Figure 2 for Real-time Denoising and Dereverberation with Tiny Recurrent U-Net
Figure 3 for Real-time Denoising and Dereverberation with Tiny Recurrent U-Net
Figure 4 for Real-time Denoising and Dereverberation with Tiny Recurrent U-Net
* 5 pages, 2 figures, 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). arXiv admin note: text overlap with arXiv:2006.00687 
   Access Paper or Ask Questions
1
2
3
>>