Search Results for author:
Found 16 papers, 2 papers with code
Spatial LibriSpeech: An Augmented Dataset for Spatial Audio Learning
We present Spatial LibriSpeech, a spatial audio dataset with over 650 hours of 19-channel audio, first-order ambisonics, and optional distractor noise.
Self-conditioning pre-trained language models
We compare our method with FUDGE and PPLM-BoW, and show that our approach is able to achieve gender parity at a lower perplexity.
Filter Distillation for Network Compression
We propose two algorithms: the first allows users to target compression to specific network property, such as number of trainable variable (footprint), and produces a compressed model that satisfies the requested property while preserving the maximum amount of spectral energy in the responses of each layer, while the second is a parameter-free heuristic that selects the compression used at each layer by trying to mimic an ideal set of uncorrelated responses.
Learning Sharing Behaviors with Arbitrary Numbers of Agents
We model the individual behavior for each agent in an interaction and then use a multi-agent fusion model to generate a summary over the expected actions of the group to render the model independent of the number of agents.
NETWORK COMPRESSION USING CORRELATION ANALYSIS OF LAYER RESPONSES
Principal Filter Analysis (PFA) is an easy to implement, yet effective method for neural network compression.
Mirroring to Build Trust in Digital Assistants
We describe experiments towards building a conversational digital assistant that considers the preferred conversational style of the user.
Speaker-Independent Speech-Driven Visual Speech Synthesis using Domain-Adapted Acoustic Models
We conclude that visual speech synthesis can significantly benefit from the powerful representation of speech in the ASR acoustic models.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Finding Experts in Transformer Models
We show that expert units are important in several ways: (1) The presence of expert units is correlated ($r^2=0. 833$) with the generalization power of TM, which allows ranking TM without requiring fine-tuning on suites of downstream tasks.
Modality Dropout for Improved Performance-driven Talking Faces
We use subjective testing to demonstrate: 1) the improvement of audiovisual-driven animation over the equivalent video-only approach, and 2) the improvement in the animation of speech-related facial movements after introducing modality dropout.
MorphGAN: One-Shot Face Synthesis GAN for Detecting Recognition Bias
Images generated using MorphGAN conserve the identity of the person in the original image, and the provided control over head pose and facial expression allows test sets to be created to identify robustness issues of a facial recognition deep network with respect to pose and expression.
Multimodal Punctuation Prediction with Contextual Dropout
Automatic speech recognition (ASR) is widely used in consumer electronics.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Challenges of Adversarial Image Augmentations
Image augmentations applied during training are crucial for the generalization performance of image classifiers.
FORML: Learning to Reweight Data for Fairness
Machine learning models are trained to minimize the mean loss for a single metric, and thus typically do not consider fairness and robustness.
Fair SA: Sensitivity Analysis for Fairness in Face Recognition
One such high impact domain is that of face recognition, with real world applications involving images affected by various degradations, such as motion blur or high exposure.
FedEmbed: Personalized Private Federated Learning
Federated learning enables the deployment of machine learning to problems for which centralized data collection is impractical.
On the role of Lip Articulation in Visual Speech Perception
Previous research has shown that traditional metrics used to optimize and assess models for generating lip motion from speech are not a good indicator of subjective opinion of animation quality.
