We present a structured overview of adaptation algorithms for neural network-based speech
recognition, considering both hybrid hidden Markov model/neural network systems and end …

Research on speech processing has traditionally considered the task of designing hand-
engineered acoustic features (feature engineering) as a separate distinct problem from the …

In this paper, we present a thorough evaluation of the efficacy of knowledge distillation and
its dependence on student and teacher architectures. Starting with the observation that more …

Abstract Knowledge distillation is a popular technique for training a small student network to
emulate a larger teacher model, such as an ensemble of networks. We show that while …

KD3A: Unsupervised Multi-Source Decentralized Domain Adaptation via Knowledge Distillation
(Appendix) Page 1 KD3A: Unsupervised Multi-Source Decentralized Domain Adaptation via …

The external language models (LM) integration remains a challenging task for end-to-end
(E2E) automatic speech recognition (ASR) which has no clear division between acoustic …

Abstract Domain generalization is the task of learning models that generalize to unseen
target domains. We propose a simple yet effective method for domain generalization, named …

While huge volumes of unlabeled data are generated and made available in many domains,
the demand for automated understanding of visual data is higher than ever before. Most …

Visual model-based RL methods typically encode image observations into low-dimensional
representations in a manner that does not eliminate redundant information. This leaves them …

In unsupervised domain adaptation (UDA), a target-domain model is trained by the
supervised knowledge from a source domain. Although UDA has recently received much …