Past work on unsupervised parsing is constrained to written form. In thi...
Transformer-based language models have shown to be very powerful for nat...
Much recent work on Spoken Language Understanding (SLU) falls short in a...
Much recent work on Spoken Language Understanding (SLU) is limited in at...
Vector Quantized Variational AutoEncoders (VQ-VAE) are a powerful
repres...
This thesis describes our ongoing work on Contrastive Predictive Coding ...
We present JHU's system submission to the ASVspoof 2019 Challenge:
Anti-...
An attacker may use a variety of techniques to fool an automatic speaker...