Deep spoken keyword spotting: An overview

I López-Espejo, ZH Tan, JHL Hansen, J Jensen - IEEE Access, 2021 - ieeexplore.ieee.org
Spoken keyword spotting (KWS) deals with the identification of keywords in audio streams
and has become a fast-growing technology thanks to the paradigm shift introduced by deep …

Efficient automation of neural network design: A survey on differentiable neural architecture search

A Heuillet, A Nasser, H Arioui, H Tabia - ACM Computing Surveys, 2024 - dl.acm.org
In the past few years, Differentiable Neural Architecture Search (DNAS) rapidly imposed
itself as the trending approach to automate the discovery of deep neural network …

Micronets: Neural network architectures for deploying tinyml applications on commodity microcontrollers

C Banbury, C Zhou, I Fedorov… - … of machine learning …, 2021 - proceedings.mlsys.org
Executing machine learning workloads locally on resource constrained microcontrollers
(MCUs) promises to drastically expand the application space of IoT. However, so-called …

Nas-bench-asr: Reproducible neural architecture search for speech recognition

A Mehrotra, AGCP Ramos, S Bhattacharya… - International …, 2021 - openreview.net
Powered by innovations in novel architecture design, noise tolerance techniques and
increasing model capacity, Automatic Speech Recognition (ASR) has made giant strides in …

AdvRush: Searching for adversarially robust neural architectures

J Mok, B Na, H Choe, S Yoon - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
Deep neural networks continue to awe the world with their remarkable performance. Their
predictions, however, are prone to be corrupted by adversarial examples that are …

Partially-connected differentiable architecture search for deepfake and spoofing detection

W Ge, M Panariello, J Patino, M Todisco… - arXiv preprint arXiv …, 2021 - arxiv.org
This paper reports the first successful application of a differentiable architecture search
(DARTS) approach to the deepfake and spoofing detection problems. An example of neural …

Neural architecture search for LF-MMI trained time delay neural networks

S Hu, X Xie, M Cui, J Deng, S Liu, J Yu… - … on Audio, Speech …, 2022 - ieeexplore.ieee.org
State-of-the-art automatic speech recognition (ASR) system development is data and
computation intensive. The optimal design of deep neural networks (DNNs) for these …

End-to-end keyword spotting using neural architecture search and quantization

D Peter, W Roth, F Pernkopf - ICASSP 2022-2022 IEEE …, 2022 - ieeexplore.ieee.org
This paper introduces neural architecture search (NAS) for the automatic discovery of end-to-
end keyword spotting (KWS) models for limited resource environments. We employ a …

Autokws: Keyword spotting with differentiable architecture search

B Zhang, W Li, Q Li, W Zhuang, X Chu… - ICASSP 2021-2021 …, 2021 - ieeexplore.ieee.org
Smart audio devices are gated by an always-on lightweight keyword spotting program to
reduce power consumption. It is however challenging to design models that have both high …

On streaming disaster damage assessment in social sensing: A crowd-driven dynamic neural architecture searching approach

Y Zhang, R Zong, Z Kou, L Shang, D Wang - Knowledge-Based Systems, 2022 - Elsevier
Motivated by the recent advances in Internet and communication techniques and the
proliferation of online social media, social sensing has emerged as a new sensing paradigm …