Recent research has shown that language models have a tendency to memori...
Federated learning (FL) can help promote data privacy by training a shar...
The bootstrap resampling method has been popular for performing signific...
We propose Neural-FST Class Language Model (NFCLM) for end-to-end speech...
Speech model adaptation is crucial to handle the discrepancy between
ser...
The issue of fairness arises when the automatic speech recognition (ASR)...
Hybrid automatic speech recognition (ASR) models are typically sequentia...
We introduce federated marginal personalization (FMP), a novel method fo...
In this work, to measure the accuracy and efficiency for a latency-contr...
Although n-gram language models (LMs) have been outperformed by the
stat...
Supervised ASR models have reached unprecedented levels of accuracy, tha...
Neural language models (LMs) have been proved to significantly outperfor...
We propose a two-layer cache mechanism to speed up dynamic WFST decoding...
In this work, we study how the large-scale pretrain-finetune framework
c...
We present a new statistical learning paradigm for Boltzmann machines ba...
Although information extraction and coreference resolution appear togeth...