追蹤
Gautham J. Mysore
Gautham J. Mysore
Senior Principal Scientist, Adobe Research
在 adobe.com 的電子郵件地址已通過驗證 - 首頁
標題
引用次數
引用次數
年份
The visual microphone: Passive recovery of sound from video
A Davis, M Rubinstein, N Wadhwa, GJ Mysore, F Durand, WT Freeman
Association for Computing Machinery (ACM), 2014
4562014
Static and dynamic source separation using nonnegative factorizations: A unified view
P Smaragdis, C Fevotte, GJ Mysore, N Mohammadiha, M Hoffman
IEEE Signal Processing Magazine 31 (3), 66-75, 2014
2302014
Non-negative hidden Markov modeling of audio with application to source separation
GJ Mysore, P Smaragdis, B Raj
International Conference on Latent Variable Analysis and Signal Separation …, 2010
1692010
FFTNet: A real-time speaker-dependent neural vocoder
Z Jin, A Finkelstein, GJ Mysore, J Lu
2018 IEEE international conference on acoustics, speech and signal …, 2018
1402018
Eulerian video magnification and analysis
N Wadhwa, HY Wu, A Davis, M Rubinstein, E Shih, GJ Mysore, JG Chen, ...
Communications of the ACM 60 (1), 87-95, 2016
1352016
Separation by “humming”: User-guided sound extraction from monophonic mixtures
P Smaragdis, GJ Mysore
2009 IEEE Workshop on Applications of Signal Processing to Audio and …, 2009
1272009
F0-consistent many-to-many non-parallel voice conversion via conditional autoencoder
K Qian, Z Jin, M Hasegawa-Johnson, GJ Mysore
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
1212020
A non-negative approach to semi-supervised separation of speech from noise with the use of temporal dynamics
GJ Mysore, P Smaragdis
2011 IEEE International Conference on Acoustics, Speech and Signal …, 2011
1182011
Universal speech models for speaker independent single channel source separation
DL Sun, GJ Mysore
2013 IEEE International Conference on Acoustics, Speech and Signal …, 2013
1052013
Can we automatically transform speech recorded on common consumer devices in real-world environments into professional production quality speech?—a dataset, insights, and …
GJ Mysore
IEEE Signal Processing Letters 22 (8), 1006-1010, 2014
1042014
System and method for acoustic echo cancellation using spectral decomposition
P Smaragdis, GJ Mysore
US Patent 8,724,798, 2014
1002014
Content-based tools for editing audio stories
S Rubin, F Berthouzoz, GJ Mysore, W Li, M Agrawala
Proceedings of the 26th annual ACM symposium on User interface software and …, 2013
952013
Fast and easy crowdsourced perceptual audio evaluation
M Cartwright, B Pardo, GJ Mysore, M Hoffman
2016 IEEE International Conference on Acoustics, Speech and Signal …, 2016
902016
A differentiable perceptual audio metric learned from just noticeable differences
P Manocha, A Finkelstein, R Zhang, NJ Bryan, GJ Mysore, Z Jin
arXiv preprint arXiv:2001.04460, 2020
862020
Voco: Text-based insertion and replacement in audio narration
Z Jin, GJ Mysore, S Diverdi, J Lu, A Finkelstein
ACM Transactions on Graphics (TOG) 36 (4), 1-13, 2017
862017
Lamello: Passive acoustic sensing for tangible input components
V Savage, A Head, B Hartmann, DB Goldman, G Mysore, W Li
Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing …, 2015
862015
Speaker and noise independent voice activity detection.
FG Germain, DL Sun, GJ Mysore
Interspeech 2013 (26), 9, 2013
772013
Online PLCA for real-time semi-supervised source separation
Z Duan, GJ Mysore, P Smaragdis
International Conference on Latent Variable Analysis and Signal Separation …, 2012
672012
Speech enhancement by online non-negative spectrogram decomposition in non-stationary noise environments.
Z Duan, GJ Mysore, P Smaragdis
INTERSPEECH, 595-598, 2012
652012
Audio-based music structure analysis: Current trends, open challenges, and applications
O Nieto, GJ Mysore, C Wang, JBL Smith, J Schlüter, T Grill, B McFee
Transactions of the International Society for Music Information Retrieval 3 (1), 2020
632020
系統目前無法執行作業,請稍後再試。
文章 1–20