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 multi-task learning, multiple tasks are solved jointly, sharing inductive bias between them.
Multi-task learning is inherently a multi-objective problem because different tasks may …

Multi-task learning is a powerful method for solving multiple correlated tasks simultaneously.
However, it is often impossible to find one single solution to optimize all the tasks, since …

Federated learning (FL) is a heavily promoted approach for training ML models on sensitive
data, eg, text typed by users on their smartphones. FL is expressly designed for training on …

In this paper, we summarize recent progresses made in deep learning based acoustic
models and the motivation and insights behind the surveyed techniques. We first discuss …

Multitask learning, ie learning several tasks at once with the same neural network, can
improve performance in each of the tasks. Designing deep neural network architectures for …

We propose a novel adversarial multi-task learning scheme, aiming at actively curtailing the
inter-talker feature variability while maximizing its senone discriminability so as to enhance …

The teacher-student (T/S) learning has been shown to be effective for a variety of problems
such as domain adaptation and model compression. One shortcoming of the T/S learning is …

This work presents a broad study on the adaptation of neural network acoustic models by
means of learning hidden unit contributions (LHUC)-a method that linearly re-combines …