research
∙
08/18/2023
Spatial LibriSpeech: An Augmented Dataset for Spatial Audio Learning
We present Spatial LibriSpeech, a spatial audio dataset with over 650 ho...
share
research
∙
03/18/2022
Towards a Perceptual Model for Estimating the Quality of Visual Speech
Generating realistic lip motions to simulate speech production is key fo...
research
∙
02/08/2022
Fair SA: Sensitivity Analysis for Fairness in Face Recognition
As the use of deep learning in high impact domains becomes ubiquitous, i...
research
∙
02/03/2022
FORML: Learning to Reweight Data for Fairness
Deployed machine learning models are evaluated by multiple metrics beyon...
research
∙
11/24/2021
Challenges of Adversarial Image Augmentations
Image augmentations applied during training are crucial for the generali...
research
∙
09/30/2021
Self-conditioning pre-trained language models
We study the presence of expert units in pre-trained Transformer-based L...
research
∙
02/12/2021
Multimodal Punctuation Prediction with Contextual Dropout
Automatic speech recognition (ASR) is widely used in consumer electronic...
research
∙
12/09/2020
MorphGAN: One-Shot Face Synthesis GAN for Detecting Recognition Bias
To detect bias in face recognition networks, it can be useful to probe a...
research
∙
05/27/2020
Modality Dropout for Improved Performance-driven Talking Faces
We describe our novel deep learning approach for driving animated faces ...
research
∙
05/15/2020
Finding Experts in Transformer Models
In this work we study the presence of expert units in pre-trained Transf...
research
∙
05/15/2019
Speaker-Independent Speech-Driven Visual Speech Synthesis using Domain-Adapted Acoustic Models
Speech-driven visual speech synthesis involves mapping features extracte...
research
∙
04/02/2019
Mirroring to Build Trust in Digital Assistants
We describe experiments towards building a conversational digital assist...
research
∙
12/10/2018
Learning Sharing Behaviors with Arbitrary Numbers of Agents
We propose a method for modeling and learning turn-taking behaviors for ...
research
∙
07/20/2018