Yashesh Gaur

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 …

CTCBERT: Advancing Hidden-unit BERT with CTC Objectives

2022 · arXiv (Cornell University)

In this work, we present a simple but effective method, CTCBERT, for advancing hidden-unit BERT (HuBERT). HuBERT applies a frame-level cross-entropy (CE) loss, which is similar to most acoustic model training. However, CTCBERT performs the …

Streaming, fast and accurate on-device Inverse Text Normalization for Automatic Speech Recognition

2022 · arXiv (Cornell University)

Automatic Speech Recognition (ASR) systems typically yield output in lexical form. However, humans prefer a written form output. To bridge this gap, ASR systems usually employ Inverse Text Normalization (ITN). In previous works, Weighted Finite …