Continual Learning, also known as Lifelong Learning, aims to continually learn from new
data as it becomes available. While prior research on continual learning in automatic …

Automatic speech recognition (ASR) technologies today are primarily optimized for given
datasets; thus, any changes in the application environment (eg, acoustic conditions or topic …

When labeled data is insufficient, pseudo-labeling based semi-supervised learning can
significantly improve the performance of automatic speech recognition. However, pseudo …

Learning a set of tasks in sequence remains a challenge for artificial neural networks, which,
in such scenarios, tend to suffer from Catastrophic Forgetting (CF). The same applies to End …

Financial fraud cases are on the rise even with the current technological advancements.
Due to the lack of inter-organization synergy and because of privacy concerns, authentic …

Audio commands are a preferred communication medium to keep inspectors in the loop of
civil infrastructure inspection performed by a semi-autonomous drone. To understand job …

Adapting Automatic Speech Recognition (ASR) models to new domains results in a
deterioration of performance on the original domain (s), a phenomenon called Catastrophic …

In this paper, we propose a Unified pre-training Framework for Online and Offline (UFO2)
Automatic Speech Recognition (ASR), which 1) simplifies the two separate training …

In this paper, we present an incremental domain adaptation technique to prevent
catastrophic forgetting for an end-to-end automatic speech recognition (ASR) model …

ABSTRACT End-to-end Automatic Speech Recognition (ASR) models are usually trained to
reduce the losses of the whole token sequences, while neglecting explicit phonemic …