Kaizhi Qian

发表

Continuous Convolutional Neural Network forNonuniform Time Series

Mark Hasegawa-Johnson, Shiyu Chang, Jishen Zhao, 2019 .

Zero-Shot Voice Style Transfer with Only Autoencoder Loss pdf

Mark Hasegawa-Johnson, Shiyu Chang, Xuesong Yang, 2019, ICML.

Speech Enhancement Using Bayesian Wavenet

Mark Hasegawa-Johnson, Shiyu Chang, Xuesong Yang, 2017, INTERSPEECH.

F0-Consistent Many-To-Many Non-Parallel Voice Conversion Via Conditional Autoencoder

Mark Hasegawa-Johnson, Gautham J. Mysore, Zeyu Jin, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

An Efficient and Margin-Approaching Zero-Confidence Adversarial Attack pdf

Mo Yu, Shiyu Chang, Yang Zhang, 2019, ArXiv.

Deep Learning Based Speech Beamforming

Mark Hasegawa-Johnson, Shiyu Chang, Xuesong Yang, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Regularized Estimation of Gaussian Mixture Models for SVM Based Speaker Recognition

Kaizhi Qian, 2014 .

Speech enhancement using deep dilated CNN

Kaizhi Qian, 2018 .

Monaural Singing Voice Separation Using Fusion-Net with Time-Frequency Masking

Mark Hasegawa-Johnson, Masato Akagi, Feng Li, 2019, 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC).

Application of local binary patterns for SVM based stop consonant detection

Mark Hasegawa-Johnson, Yang Zhang, Kaizhi Qian, 2016 .

Unsupervised Speech Decomposition via Triple Information Bottleneck pdf

Mark Hasegawa-Johnson, Shiyu Chang, David Cox, 2020, ICML.

Deep Network Perceptual Losses for Speech Denoising pdf

Yang Zhang, Josh H. McDermott, Kaizhi Qian, 2020, ArXiv.

Speech Denoising with Auditory Models

Josh H. McDermott, Kaizhi Qian, Andrew Francl, 2020, Interspeech.

Global Rhythm Style Transfer Without Text Transcriptions pdf

Chuang Gan, Mark Hasegawa-Johnson, Shiyu Chang, 2021, ArXiv.

Continuous Cnn For Nonuniform Time Series

Mark Hasegawa-Johnson, Shiyu Chang, Yang Zhang, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

On the Interplay Between Sparsity, Naturalness, Intelligibility, and Prosody in Speech Synthesis pdf

James Glass, Junichi Yamagishi, Shiyu Chang, 2021, ArXiv.

Global Prosody Style Transfer Without Text Transcriptions

Chuang Gan, Mark Hasegawa-Johnson, Shiyu Chang, 2021, ICML.

PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition pdf

James Glass, Shiyu Chang, Yang Zhang, 2021, ArXiv.