Kenichi Kumatani

Dynamic Gradient Aggregation for Federated Domain Adaptation

2021 · arXiv (Cornell University)

In this paper, a new learning algorithm for Federated Learning (FL) is introduced. The proposed scheme is based on a weighted gradient aggregation using two-step optimization to offer a flexible training pipeline. Herein, two different …

Deploying self-supervised learning in the wild for hybrid automatic speech recognition

2022 · arXiv (Cornell University)

Self-supervised learning (SSL) methods have proven to be very successful in automatic speech recognition (ASR). These great improvements have been reported mostly based on highly curated datasets such as LibriSpeech for non-streaming End-to-End ASR models. …