133 citations · 300 across the 26 of their papers we have counts for
7 papers · 1 filter
Training Robust Zero-Shot Voice Conversion Models with Self-supervised Features
Trung Dang, Dung Tran, Peter Chin +1
Unsupervised Zero-Shot Voice Conversion (VC) aims to modify the speaker characteristic of an utterance to match an unseen target speaker without relying on parallel training data.…
Revealing and Protecting Labels in Distributed Training
Trung Dang, Om Thakkar, Swaroop Ramaswamy +3
Distributed learning paradigms such as federated learning often involve transmission of model updates, or gradients, over a network, thereby avoiding transmission of private data.…
What is Learned in Knowledge Graph Embeddings?
Michael R. Douglas, Michael Simkin, Omri Ben-Eliezer +4
A knowledge graph (KG) is a data structure which represents entities and relations as the vertices and edges of a directed graph with edge types. KGs are an important primitive in…
RetroGAN: A Cyclic Post-Specialization System for Improving Out-of-Knowledge and Rare Word Representations
Pedro Colon-Hernandez, Yida Xin, Henry Lieberman +3
Retrofitting is a technique used to move word vectors closer together or further apart in their space to reflect their relationships in a Knowledge Base (KB). However, retrofitting…
Substitutional Neural Image Compression
Xiao Wang, Wei Jiang, Wei Wang +3
We describe Substitutional Neural Image Compression (SNIC), a general approach for enhancing any neural image compression model, that requires no data or additional tuning of the t…
A Method to Reveal Speaker Identity in Distributed ASR Training, and How to Counter It
Trung Dang, Om Thakkar, Swaroop Ramaswamy +3
End-to-end Automatic Speech Recognition (ASR) models are commonly trained over spoken utterances using optimization methods like Stochastic Gradient Descent (SGD). In distributed s…
Revisiting the Prepositional-Phrase Attachment Problem Using Explicit Commonsense Knowledge
Yida Xin, Henry Lieberman, Peter Chin
We revisit the challenging problem of resolving prepositional-phrase (PP) attachment ambiguity. To date, proposed solutions are either rule-based, where explicit grammar rules dire…