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 …

A 510-nW wake-up keyword-spotting chip using serial-FFT-based MFCC and binarized depthwise separable CNN in 28-nm CMOS

W Shan, M Yang, T Wang, Y Lu, H Cai… - IEEE Journal of Solid …, 2020 - ieeexplore.ieee.org
We propose a sub-μW always-ON keyword spotting (μKWS) chip for audio wake-up
systems. It is mainly composed of a neural network (NN) and a feature extraction (FE) circuit …

How to design a three-stage architecture for audio-visual active speaker detection in the wild

O Köpüklü, M Taseska, G Rigoll - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
Successful active speaker detection requires a three-stage pipeline:(i) audio-visual
encoding for all speakers in the clip,(ii) inter-speaker relation modeling between a reference …

Multichannel speech enhancement by raw waveform-mapping using fully convolutional networks

CL Liu, SW Fu, YJ Li, JW Huang… - … /ACM Transactions on …, 2020 - ieeexplore.ieee.org
In recent years, waveform-mapping-based speech enhancement (SE) methods have
garnered significant attention. These methods generally use a deep learning model to …

Hardware acceleration for embedded keyword spotting: Tutorial and survey

JSP Giraldo, M Verhelst - ACM Transactions on Embedded Computing …, 2021 - dl.acm.org
In recent years, Keyword Spotting (KWS) has become a crucial human–machine interface
for mobile devices, allowing users to interact more naturally with their gadgets by leveraging …

Small-footprint keyword spotting with multi-scale temporal convolution

X Li, X Wei, X Qin - arXiv preprint arXiv:2010.09960, 2020 - arxiv.org
Keyword Spotting (KWS) plays a vital role in human-computer interaction for smart on-
device terminals and service robots. It remains challenging to achieve the trade-off between …

Phonmatchnet: phoneme-guided zero-shot keyword spotting for user-defined keywords

YH Lee, N Cho - arXiv preprint arXiv:2308.16511, 2023 - arxiv.org
This study presents a novel zero-shot user-defined keyword spotting model that utilizes the
audio-phoneme relationship of the keyword to improve performance. Unlike the previous …

Neural architecture search for keyword spotting

T Mo, Y Yu, M Salameh, D Niu, S Jui - arXiv preprint arXiv:2009.00165, 2020 - arxiv.org
Deep neural networks have recently become a popular solution to keyword spotting
systems, which enable the control of smart devices via voice. In this paper, we apply neural …

A 2.5 μW KWS Engine With Pruned LSTM and Embedded MFCC for IoT Applications

YS Chong, WL Goh, VP Nambiar… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
Always-on keyword spotting (KWS) hardware is gaining popularity in ultra-low power IoT
applications where specific words are used to wake up and activate the power hungry …

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 …