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 Yi-Hsuan Yang

Yi-Hsuan Yang

Automatic DJ Transitions with Differentiable Audio Effects and Generative Adversarial Networks


Oct 13, 2021
Bo-Yu Chen, Wei-Han Hsu, Wei-Hsiang Liao, Marco A. Martínez Ramírez, Yuki Mitsufuji, Yi-Hsuan Yang

Figure 1 for Automatic DJ Transitions with Differentiable Audio Effects and Generative Adversarial Networks
Figure 2 for Automatic DJ Transitions with Differentiable Audio Effects and Generative Adversarial Networks
Figure 3 for Automatic DJ Transitions with Differentiable Audio Effects and Generative Adversarial Networks
Figure 4 for Automatic DJ Transitions with Differentiable Audio Effects and Generative Adversarial Networks
* Submitted to ICASSP 2022 
  Access Paper or Ask Questions

KaraSinger: Score-Free Singing Voice Synthesis with VQ-VAE using Mel-spectrograms


Oct 08, 2021
Chien-Feng Liao, Jen-Yu Liu, Yi-Hsuan Yang

Figure 1 for KaraSinger: Score-Free Singing Voice Synthesis with VQ-VAE using Mel-spectrograms
Figure 2 for KaraSinger: Score-Free Singing Voice Synthesis with VQ-VAE using Mel-spectrograms
Figure 3 for KaraSinger: Score-Free Singing Voice Synthesis with VQ-VAE using Mel-spectrograms
Figure 4 for KaraSinger: Score-Free Singing Voice Synthesis with VQ-VAE using Mel-spectrograms
* Submitted to ICASSP 2022 
  Access Paper or Ask Questions

Variable-Length Music Score Infilling via XLNet and Musically Specialized Positional Encoding


Aug 11, 2021
Chin-Jui Chang, Chun-Yi Lee, Yi-Hsuan Yang

Figure 1 for Variable-Length Music Score Infilling via XLNet and Musically Specialized Positional Encoding
Figure 2 for Variable-Length Music Score Infilling via XLNet and Musically Specialized Positional Encoding
Figure 3 for Variable-Length Music Score Infilling via XLNet and Musically Specialized Positional Encoding
Figure 4 for Variable-Length Music Score Infilling via XLNet and Musically Specialized Positional Encoding
* The paper has been accepted for publication at ISMIR 2021 
  Access Paper or Ask Questions

A Benchmarking Initiative for Audio-Domain Music Generation Using the Freesound Loop Dataset


Aug 03, 2021
Tun-Min Hung, Bo-Yu Chen, Yen-Tung Yeh, Yi-Hsuan Yang

Figure 1 for A Benchmarking Initiative for Audio-Domain Music Generation Using the Freesound Loop Dataset
Figure 2 for A Benchmarking Initiative for Audio-Domain Music Generation Using the Freesound Loop Dataset
Figure 3 for A Benchmarking Initiative for Audio-Domain Music Generation Using the Freesound Loop Dataset
Figure 4 for A Benchmarking Initiative for Audio-Domain Music Generation Using the Freesound Loop Dataset
* The paper has been accepted for publication at ISMIR 2021 
  Access Paper or Ask Questions

EMOPIA: A Multi-Modal Pop Piano Dataset For Emotion Recognition and Emotion-based Music Generation


Aug 03, 2021
Hsiao-Tzu Hung, Joann Ching, Seungheon Doh, Nabin Kim, Juhan Nam, Yi-Hsuan Yang

Figure 1 for EMOPIA: A Multi-Modal Pop Piano Dataset For Emotion Recognition and Emotion-based Music Generation
Figure 2 for EMOPIA: A Multi-Modal Pop Piano Dataset For Emotion Recognition and Emotion-based Music Generation
Figure 3 for EMOPIA: A Multi-Modal Pop Piano Dataset For Emotion Recognition and Emotion-based Music Generation
Figure 4 for EMOPIA: A Multi-Modal Pop Piano Dataset For Emotion Recognition and Emotion-based Music Generation
* The paper has been accepted for publication at ISMIR 2021 
  Access Paper or Ask Questions

DadaGP: A Dataset of Tokenized GuitarPro Songs for Sequence Models


Jul 30, 2021
Pedro Sarmento, Adarsh Kumar, CJ Carr, Zack Zukowski, Mathieu Barthet, Yi-Hsuan Yang

Figure 1 for DadaGP: A Dataset of Tokenized GuitarPro Songs for Sequence Models
Figure 2 for DadaGP: A Dataset of Tokenized GuitarPro Songs for Sequence Models
Figure 3 for DadaGP: A Dataset of Tokenized GuitarPro Songs for Sequence Models
Figure 4 for DadaGP: A Dataset of Tokenized GuitarPro Songs for Sequence Models

  Access Paper or Ask Questions

MidiBERT-Piano: Large-scale Pre-training for Symbolic Music Understanding


Jul 12, 2021
Yi-Hui Chou, I-Chun Chen, Chin-Jui Chang, Joann Ching, Yi-Hsuan Yang

Figure 1 for MidiBERT-Piano: Large-scale Pre-training for Symbolic Music Understanding
Figure 2 for MidiBERT-Piano: Large-scale Pre-training for Symbolic Music Understanding
Figure 3 for MidiBERT-Piano: Large-scale Pre-training for Symbolic Music Understanding
Figure 4 for MidiBERT-Piano: Large-scale Pre-training for Symbolic Music Understanding

  Access Paper or Ask Questions

Source Separation-based Data Augmentation for Improved Joint Beat and Downbeat Tracking


Jun 16, 2021
Ching-Yu Chiu, Joann Ching, Wen-Yi Hsiao, Yu-Hua Chen, Alvin Wen-Yu Su, Yi-Hsuan Yang

Figure 1 for Source Separation-based Data Augmentation for Improved Joint Beat and Downbeat Tracking
Figure 2 for Source Separation-based Data Augmentation for Improved Joint Beat and Downbeat Tracking
Figure 3 for Source Separation-based Data Augmentation for Improved Joint Beat and Downbeat Tracking
Figure 4 for Source Separation-based Data Augmentation for Improved Joint Beat and Downbeat Tracking
* Accepted to European Signal Processing Conference (EUSIPCO 2021) 
  Access Paper or Ask Questions

Drum-Aware Ensemble Architecture for Improved Joint Musical Beat and Downbeat Tracking


Jun 16, 2021
Ching-Yu Chiu, Alvin Wen-Yu Su, Yi-Hsuan Yang

Figure 1 for Drum-Aware Ensemble Architecture for Improved Joint Musical Beat and Downbeat Tracking
Figure 2 for Drum-Aware Ensemble Architecture for Improved Joint Musical Beat and Downbeat Tracking
Figure 3 for Drum-Aware Ensemble Architecture for Improved Joint Musical Beat and Downbeat Tracking
Figure 4 for Drum-Aware Ensemble Architecture for Improved Joint Musical Beat and Downbeat Tracking
* Accepted to IEEE Signal Processing Letters (May 2021) 
  Access Paper or Ask Questions

Relative Positional Encoding for Transformers with Linear Complexity


Jun 10, 2021
Antoine Liutkus, Ondřej Cífka, Shih-Lun Wu, Umut Şimşekli, Yi-Hsuan Yang, Gaël Richard

Figure 1 for Relative Positional Encoding for Transformers with Linear Complexity
Figure 2 for Relative Positional Encoding for Transformers with Linear Complexity
Figure 3 for Relative Positional Encoding for Transformers with Linear Complexity
Figure 4 for Relative Positional Encoding for Transformers with Linear Complexity
* ICML 2021 (long talk) camera-ready. 24 pages 
  Access Paper or Ask Questions

MuseMorphose: Full-Song and Fine-Grained Music Style Transfer with Just One Transformer VAE


May 10, 2021
Shih-Lun Wu, Yi-Hsuan Yang

Figure 1 for MuseMorphose: Full-Song and Fine-Grained Music Style Transfer with Just One Transformer VAE
Figure 2 for MuseMorphose: Full-Song and Fine-Grained Music Style Transfer with Just One Transformer VAE
Figure 3 for MuseMorphose: Full-Song and Fine-Grained Music Style Transfer with Just One Transformer VAE
Figure 4 for MuseMorphose: Full-Song and Fine-Grained Music Style Transfer with Just One Transformer VAE
* Preprint. 26 pages, 7 figures, and 8 tables 
  Access Paper or Ask Questions

Compound Word Transformer: Learning to Compose Full-Song Music over Dynamic Directed Hypergraphs


Jan 07, 2021
Wen-Yi Hsiao, Jen-Yu Liu, Yin-Cheng Yeh, Yi-Hsuan Yang

Figure 1 for Compound Word Transformer: Learning to Compose Full-Song Music over Dynamic Directed Hypergraphs
Figure 2 for Compound Word Transformer: Learning to Compose Full-Song Music over Dynamic Directed Hypergraphs
Figure 3 for Compound Word Transformer: Learning to Compose Full-Song Music over Dynamic Directed Hypergraphs
Figure 4 for Compound Word Transformer: Learning to Compose Full-Song Music over Dynamic Directed Hypergraphs

  Access Paper or Ask Questions

Mixing-Specific Data Augmentation Techniques for Improved Blind Violin/Piano Source Separation


Aug 06, 2020
Ching-Yu Chiu, Wen-Yi Hsiao, Yin-Cheng Yeh, Yi-Hsuan Yang, Alvin Wen-Yu Su

Figure 1 for Mixing-Specific Data Augmentation Techniques for Improved Blind Violin/Piano Source Separation
Figure 2 for Mixing-Specific Data Augmentation Techniques for Improved Blind Violin/Piano Source Separation
Figure 3 for Mixing-Specific Data Augmentation Techniques for Improved Blind Violin/Piano Source Separation
Figure 4 for Mixing-Specific Data Augmentation Techniques for Improved Blind Violin/Piano Source Separation
* Accepted to IEEE 22nd International Workshop on Multimedia Signal Processing (MMSP 2020) 
  Access Paper or Ask Questions

Neural Loop Combiner: Neural Network Models for Assessing the Compatibility of Loops


Aug 05, 2020
Bo-Yu Chen, Jordan B. L. Smith, Yi-Hsuan Yang

Figure 1 for Neural Loop Combiner: Neural Network Models for Assessing the Compatibility of Loops
Figure 2 for Neural Loop Combiner: Neural Network Models for Assessing the Compatibility of Loops
Figure 3 for Neural Loop Combiner: Neural Network Models for Assessing the Compatibility of Loops
Figure 4 for Neural Loop Combiner: Neural Network Models for Assessing the Compatibility of Loops
* Accepted to the 21st International Society for Music Information Retrieval Conference (ISMIR 2020) 
  Access Paper or Ask Questions

The Jazz Transformer on the Front Line: Exploring the Shortcomings of AI-composed Music through Quantitative Measures


Aug 04, 2020
Shih-Lun Wu, Yi-Hsuan Yang

Figure 1 for The Jazz Transformer on the Front Line: Exploring the Shortcomings of AI-composed Music through Quantitative Measures
Figure 2 for The Jazz Transformer on the Front Line: Exploring the Shortcomings of AI-composed Music through Quantitative Measures
Figure 3 for The Jazz Transformer on the Front Line: Exploring the Shortcomings of AI-composed Music through Quantitative Measures
Figure 4 for The Jazz Transformer on the Front Line: Exploring the Shortcomings of AI-composed Music through Quantitative Measures
* Accepted to the 21st International Society for Music Information Retrieval Conference (ISMIR 2020) 
  Access Paper or Ask Questions

Speech-to-Singing Conversion based on Boundary Equilibrium GAN


May 30, 2020
Da-Yi Wu, Yi-Hsuan Yang

Figure 1 for Speech-to-Singing Conversion based on Boundary Equilibrium GAN
Figure 2 for Speech-to-Singing Conversion based on Boundary Equilibrium GAN
Figure 3 for Speech-to-Singing Conversion based on Boundary Equilibrium GAN
Figure 4 for Speech-to-Singing Conversion based on Boundary Equilibrium GAN

  Access Paper or Ask Questions

Unconditional Audio Generation with Generative Adversarial Networks and Cycle Regularization


May 18, 2020
Jen-Yu Liu, Yu-Hua Chen, Yin-Cheng Yeh, Yi-Hsuan Yang

Figure 1 for Unconditional Audio Generation with Generative Adversarial Networks and Cycle Regularization
Figure 2 for Unconditional Audio Generation with Generative Adversarial Networks and Cycle Regularization
Figure 3 for Unconditional Audio Generation with Generative Adversarial Networks and Cycle Regularization
Figure 4 for Unconditional Audio Generation with Generative Adversarial Networks and Cycle Regularization

  Access Paper or Ask Questions

A Comparative Study of Western and Chinese Classical Music based on Soundscape Models


Feb 20, 2020
Jianyu Fan, Yi-Hsuan Yang, Kui Dong, Philippe Pasquier

Figure 1 for A Comparative Study of Western and Chinese Classical Music based on Soundscape Models
Figure 2 for A Comparative Study of Western and Chinese Classical Music based on Soundscape Models
Figure 3 for A Comparative Study of Western and Chinese Classical Music based on Soundscape Models
Figure 4 for A Comparative Study of Western and Chinese Classical Music based on Soundscape Models
* Paper accepted for 45th International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2020) 
  Access Paper or Ask Questions

Addressing the confounds of accompaniments in singer identification


Feb 17, 2020
Tsung-Han Hsieh, Kai-Hsiang Cheng, Zhe-Cheng Fan, Yu-Ching Yang, Yi-Hsuan Yang

Figure 1 for Addressing the confounds of accompaniments in singer identification
Figure 2 for Addressing the confounds of accompaniments in singer identification
Figure 3 for Addressing the confounds of accompaniments in singer identification
Figure 4 for Addressing the confounds of accompaniments in singer identification

  Access Paper or Ask Questions

Speech-to-Singing Conversion in an Encoder-Decoder Framework


Feb 16, 2020
Jayneel Parekh, Preeti Rao, Yi-Hsuan Yang

Figure 1 for Speech-to-Singing Conversion in an Encoder-Decoder Framework
Figure 2 for Speech-to-Singing Conversion in an Encoder-Decoder Framework
Figure 3 for Speech-to-Singing Conversion in an Encoder-Decoder Framework
Figure 4 for Speech-to-Singing Conversion in an Encoder-Decoder Framework
* Accepted at IEEE ICASSP 2020 
  Access Paper or Ask Questions

Pop Music Transformer: Generating Music with Rhythm and Harmony


Feb 01, 2020
Yu-Siang Huang, Yi-Hsuan Yang

Figure 1 for Pop Music Transformer: Generating Music with Rhythm and Harmony
Figure 2 for Pop Music Transformer: Generating Music with Rhythm and Harmony
Figure 3 for Pop Music Transformer: Generating Music with Rhythm and Harmony
Figure 4 for Pop Music Transformer: Generating Music with Rhythm and Harmony

  Access Paper or Ask Questions

Automatic Melody Harmonization with Triad Chords: A Comparative Study


Jan 08, 2020
Yin-Cheng Yeh, Wen-Yi Hsiao, Satoru Fukayama, Tetsuro Kitahara, Benjamin Genchel, Hao-Min Liu, Hao-Wen Dong, Yian Chen, Terence Leong, Yi-Hsuan Yang

Figure 1 for Automatic Melody Harmonization with Triad Chords: A Comparative Study
Figure 2 for Automatic Melody Harmonization with Triad Chords: A Comparative Study
Figure 3 for Automatic Melody Harmonization with Triad Chords: A Comparative Study
Figure 4 for Automatic Melody Harmonization with Triad Chords: A Comparative Study
* 20 pages, 6 figures, submitted to JNMR 
  Access Paper or Ask Questions

Score and Lyrics-Free Singing Voice Generation


Dec 26, 2019
Jen-Yu Liu, Yu-Hua Chen, Yin-Cheng Yeh, Yi-Hsuan Yang

Figure 1 for Score and Lyrics-Free Singing Voice Generation
Figure 2 for Score and Lyrics-Free Singing Voice Generation
Figure 3 for Score and Lyrics-Free Singing Voice Generation
Figure 4 for Score and Lyrics-Free Singing Voice Generation

  Access Paper or Ask Questions

Improving Automatic Jazz Melody Generation by Transfer Learning Techniques


Aug 26, 2019
Hsiao-Tzu Hung, Chung-Yang Wang, Yi-Hsuan Yang, Hsin-Min Wang

Figure 1 for Improving Automatic Jazz Melody Generation by Transfer Learning Techniques
Figure 2 for Improving Automatic Jazz Melody Generation by Transfer Learning Techniques
Figure 3 for Improving Automatic Jazz Melody Generation by Transfer Learning Techniques
Figure 4 for Improving Automatic Jazz Melody Generation by Transfer Learning Techniques
* 8 pages, Accepted to APSIPA ASC(Asia-Pacific Signal and Information Processing Association Annual Summit and Conference ) 2019 
  Access Paper or Ask Questions

Dilated Convolution with Dilated GRU for Music Source Separation


Jun 04, 2019
Jen-Yu Liu, Yi-Hsuan Yang

Figure 1 for Dilated Convolution with Dilated GRU for Music Source Separation
Figure 2 for Dilated Convolution with Dilated GRU for Music Source Separation
Figure 3 for Dilated Convolution with Dilated GRU for Music Source Separation
Figure 4 for Dilated Convolution with Dilated GRU for Music Source Separation

  Access Paper or Ask Questions

Towards a Deeper Understanding of Adversarial Losses


Jan 25, 2019
Hao-Wen Dong, Yi-Hsuan Yang

Figure 1 for Towards a Deeper Understanding of Adversarial Losses
Figure 2 for Towards a Deeper Understanding of Adversarial Losses
Figure 3 for Towards a Deeper Understanding of Adversarial Losses
Figure 4 for Towards a Deeper Understanding of Adversarial Losses

  Access Paper or Ask Questions

Training Generative Adversarial Networks with Binary Neurons by End-to-end Backpropagation


Oct 10, 2018
Hao-Wen Dong, Yi-Hsuan Yang

Figure 1 for Training Generative Adversarial Networks with Binary Neurons by End-to-end Backpropagation
Figure 2 for Training Generative Adversarial Networks with Binary Neurons by End-to-end Backpropagation
Figure 3 for Training Generative Adversarial Networks with Binary Neurons by End-to-end Backpropagation
Figure 4 for Training Generative Adversarial Networks with Binary Neurons by End-to-end Backpropagation

  Access Paper or Ask Questions

Convolutional Generative Adversarial Networks with Binary Neurons for Polyphonic Music Generation


Oct 06, 2018
Hao-Wen Dong, Yi-Hsuan Yang

Figure 1 for Convolutional Generative Adversarial Networks with Binary Neurons for Polyphonic Music Generation
Figure 2 for Convolutional Generative Adversarial Networks with Binary Neurons for Polyphonic Music Generation
Figure 3 for Convolutional Generative Adversarial Networks with Binary Neurons for Polyphonic Music Generation
Figure 4 for Convolutional Generative Adversarial Networks with Binary Neurons for Polyphonic Music Generation
* A preliminary version of this paper appeared in ISMIR 2018. In this version, we added an appendix to provide figures of sample results and remarks on the end-to-end models 
  Access Paper or Ask Questions