research
∙
12/14/2020
REDAT: Accent-Invariant Representation for End-to-End ASR by Domain Adversarial Training with Relabeling
Accents mismatching is a critical problem for end-to-end ASR. This paper...
share
research
∙
09/30/2019
Semi-supervised voice conversion with amortized variational inference
In this work we introduce a semi-supervised approach to the voice conver...
research
∙
06/20/2019
Improving Branch Prediction By Modeling Global History with Convolutional Neural Networks
CPU branch prediction has hit a wall--existing techniques achieve near-p...
research
∙
05/10/2019
Semi-supervised and Population Based Training for Voice Commands Recognition
We present a rapid design methodology that combines automated hyper-para...
research
∙
05/09/2019
Adversarially Trained Autoencoders for Parallel-Data-Free Voice Conversion
We present a method for converting the voices between a set of speakers....
research
∙
04/30/2019