1 code implementation • 25 Oct 2023 • Aaron Gokaslan, A. Feder Cooper, Jasmine Collins, Landan Seguin, Austin Jacobson, Mihir Patel, Jonathan Frankle, Cory Stephenson, Volodymyr Kuleshov
This task presents two challenges: (1) high-resolution CC images lack the captions necessary to train text-to-image generative models; (2) CC images are relatively scarce.
1 code implementation • 2 Jun 2022 • Jacob Portes, Davis Blalock, Cory Stephenson, Jonathan Frankle
Benchmarking the tradeoff between neural network accuracy and training time is computationally expensive.
no code implementations • 26 Aug 2021 • Cory Stephenson, Tyler Lee
This model is based on the hypothesis that the training data contains features that are slow to learn but informative.
no code implementations • ICLR 2021 • Cory Stephenson, Suchismita Padhy, Abhinav Ganesh, Yue Hui, Hanlin Tang, SueYeon Chung
Understanding how large neural networks avoid memorizing training data is key to explaining their high generalization performance.
1 code implementation • ICML 2020 • Jonathan Mamou, Hang Le, Miguel Del Rio, Cory Stephenson, Hanlin Tang, Yoon Kim, SueYeon Chung
In addition, we find that the emergence of linear separability in these manifolds is driven by a combined reduction of manifolds' radius, dimensionality and inter-manifold correlations.
1 code implementation • NeurIPS 2019 • Cory Stephenson, Jenelle Feather, Suchismita Padhy, Oguz Elibol, Hanlin Tang, Josh Mcdermott, SueYeon Chung
Higher level concepts such as parts-of-speech and context dependence also emerge in the later layers of the network.
no code implementations • 30 Sep 2019 • Cory Stephenson, Gokce Keskin, Anil Thomas, Oguz H. Elibol
In this work we introduce a semi-supervised approach to the voice conversion problem, in which speech from a source speaker is converted into speech of a target speaker.
no code implementations • 28 May 2019 • Suchismita Padhy, Jenelle Feather, Cory Stephenson, Oguz Elibol, Hanlin Tang, Josh Mcdermott, SueYeon Chung
The success of deep neural networks in visual tasks have motivated recent theoretical and empirical work to understand how these networks operate.
no code implementations • 9 May 2019 • Orhan Ocal, Oguz H. Elibol, Gokce Keskin, Cory Stephenson, Anil Thomas, Kannan Ramchandran
Due to the use of a single encoder, our method can generalize to converting the voice of out-of-training speakers to speakers in the training dataset.
no code implementations • 30 Apr 2019 • Gokce Keskin, Tyler Lee, Cory Stephenson, Oguz H. Elibol
We present a Cycle-GAN based many-to-many voice conversion method that can convert between speakers that are not in the training set.
no code implementations • 27 Apr 2018 • Jeff Hetherly, Paul Gamble, Maria Barrios, Cory Stephenson, Karl Ni
We propose an algorithm to denoise speakers from a single microphone in the presence of non-stationary and dynamic noise.
1 code implementation • 12 May 2017 • Cory Stephenson, Patrick Callier, Abhinav Ganesh, Karl Ni
Although the matrix determined by the output weights is dependent on a set of known speakers, we only use the input vectors during inference.