The ability to learn new concepts sequentially is a major weakness for modern neural networks, which hinders their use in non-stationary environments. Their propensity to fit the …
Intrusion detection is a form of anomalous activity detection in communication network traffic. Continual learning (CL) approaches to the intrusion detection task accumulate old …
U Michieli, PP Parada, M Ozay - arXiv preprint arXiv:2307.12660, 2023 - arxiv.org
Keyword Spotting (KWS) models on embedded devices should adapt fast to new user- defined words without forgetting previous ones. Embedded devices have limited storage …
A Diwan, CF Yeh, WN Hsu, P Tomasello… - ICASSP 2023-2023 …, 2023 - ieeexplore.ieee.org
Automatic speech recognition research focuses on training and evaluating on static datasets. Yet, as speech models are increasingly deployed on personal devices, such …
Recently, neural networks have shown impressive progress across diverse fields, with speech processing being no exception. However, recent breakthroughs in this area require …
R Flynn, A Ragni - arXiv preprint arXiv:2306.16903, 2023 - arxiv.org
While external language models (LMs) are often incorporated into the decoding stage of automated speech recognition systems, these models usually operate with limited context …
Emotions provide critical information regarding a person's health and well-being. Therefore, the ability to track emotion and patterns in emotion over time could provide new …
Emotion conveys abundant information that can improve the user experience of various automated systems, in addition to communicating information important for managing …
Continual learning has emerged as an increasingly important challenge across various tasks, including Spoken Language Understanding (SLU). In SLU, its objective is to …