43 citations · 89 across the 12 of their papers we have counts for
12 papers
Fast Benchmarking of Accuracy vs. Training Time with Cyclic Learning Rates
Jacob Portes, Davis Blalock, Cory Stephenson +1
Benchmarking the tradeoff between neural network accuracy and training time is computationally expensive. Here we show how a multiplicative cyclic learning rate schedule can be use…
When and how epochwise double descent happens
Cory Stephenson, Tyler Lee
Deep neural networks are known to exhibit a `double descent' behavior as the number of parameters increases. Recently, it has also been shown that an `epochwise double descent' eff…
On the geometry of generalization and memorization in deep neural networks
Cory Stephenson, Suchismita Padhy, Abhinav Ganesh +3
Understanding how large neural networks avoid memorizing training data is key to explaining their high generalization performance. To examine the structure of when and where memori…
Emergence of Separable Manifolds in Deep Language Representations
Jonathan Mamou, Hang Le, Miguel Del Rio +4
Deep neural networks (DNNs) have shown much empirical success in solving perceptual tasks across various cognitive modalities. While they are only loosely inspired by the biologica…
Untangling in Invariant Speech Recognition
Cory Stephenson, Jenelle Feather, Suchismita Padhy +4
Encouraged by the success of deep neural networks on a variety of visual tasks, much theoretical and experimental work has been aimed at understanding and interpreting how vision n…
Semi-supervised voice conversion with amortized variational inference
Cory Stephenson, Gokce Keskin, Anil Thomas +1
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. The propos…
Measuring the Effectiveness of Voice Conversion on Speaker Identification and Automatic Speech Recognition Systems
Gokce Keskin, Tyler Lee, Cory Stephenson +1
This paper evaluates the effectiveness of a Cycle-GAN based voice converter (VC) on four speaker identification (SID) systems and an automated speech recognition (ASR) system for v…
Adversarially Trained Autoencoders for Parallel-Data-Free Voice Conversion
Orhan Ocal, Oguz H. Elibol, Gokce Keskin +3
We present a method for converting the voices between a set of speakers. Our method is based on training multiple autoencoder paths, where there is a single speaker-independent enc…
Many-to-Many Voice Conversion with Out-of-Dataset Speaker Support
Gokce Keskin, Tyler Lee, Cory Stephenson +1
We present a Cycle-GAN based many-to-many voice conversion method that can convert between speakers that are not in the training set. This property is enabled through speaker embed…
Voices Obscured in Complex Environmental Settings (VOICES) corpus
Colleen Richey, Maria A. Barrios, Zeb Armstrong +11
This paper introduces the Voices Obscured In Complex Environmental Settings (VOICES) corpus, a freely available dataset under Creative Commons BY 4.0. This dataset will promote spe…
Deep Speech Denoising with Vector Space Projections
Jeff Hetherly, Paul Gamble, Maria Barrios +2
We propose an algorithm to denoise speakers from a single microphone in the presence of non-stationary and dynamic noise. Our approach is inspired by the recent success of neural n…
Monaural Audio Speaker Separation with Source Contrastive Estimation
Cory Stephenson, Patrick Callier, Abhinav Ganesh +1
We propose an algorithm to separate simultaneously speaking persons from each other, the "cocktail party problem", using a single microphone. Our approach involves a deep recurrent…