Automatic Speech Recognition (ASR) has historically been a driving force behind many
machine learning (ML) techniques, including the ubiquitously used hidden Markov model …

This paper presents a brief survey on Automatic Speech Recognition and discusses the
major themes and advances made in the past 60 years of research, so as to provide a …

A recent trend in artificial intelligence is the use of pretrained models for language and
vision tasks, which have achieved extraordinary performance but also puzzling failures …

A key challenge to visualization authoring is the process of getting familiar with the complex
user interfaces of authoring tools. Natural Language Interface (NLI) presents promising …

It is well known that active learning can simultaneously improve the quality of the
classification model and decrease the complexity of training instances. However, several …

With the development of multi-modal man-machine interaction, audio signal analysis is
gaining importance in a field traditionally dominated by video. In particular, anomalous …

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

Active learning is used for classification when labeling data are costly, while the main
challenge is to identify the critical instances that should be labeled. Clustering-based …

A survey of research on spoken language understanding is presented. It covers aspects of
knowledge representation, automatic interpretation strategies, semantic grammars …

We propose a unified global entropy reduction maximization (GERM) framework for active
learning and semi-supervised learning for speech recognition. Active learning aims to select …