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 …

mSilent: Towards general corpus silent speech recognition using COTS mmWave radar

S Zeng, H Wan, S Shi, W Wang - Proceedings of the ACM on Interactive …, 2023 - dl.acm.org
Silent speech recognition (SSR) allows users to speak to the device without making a
sound, avoiding being overheard or disturbing others. Compared to the video-based …

Wav2kws: Transfer learning from speech representations for keyword spotting

D Seo, HS Oh, Y Jung - IEEE Access, 2021 - ieeexplore.ieee.org
With the expanding development of on-device artificial intelligence, voice-enabled devices
such as smart speakers, wearables, and other on-device or edge processing systems have …

Learning efficient representations for keyword spotting with triplet loss

R Vygon, N Mikhaylovskiy - … 2021, St. Petersburg, Russia, September 27 …, 2021 - Springer
In the past few years, triplet loss-based metric embeddings have become a de-facto
standard for several important computer vision problems, most notably, person …

Firefox voice: An open and extensible voice assistant built upon the web

J Cambre, AC Williams, A Razi, I Bicking… - Proceedings of the …, 2021 - dl.acm.org
Voice assistants are fundamentally changing the way we access information. However,
voice assistants still leverage little about the web beyond simple search results. We …

Temporal early exiting for streaming speech commands recognition

R Tang, K Kumar, J Xin, P Vyas, W Li… - ICASSP 2022-2022 …, 2022 - ieeexplore.ieee.org
Limited-vocabulary speech commands recognition is the task of classifying a short utterance
as one of several speech commands, for which neural networks obtain state-of-the-art …

QbyE-MLPMixer: query-by-example open-vocabulary keyword spotting using MLPMixer

J Huang, W Gharbieh, Q Wan, HS Shim… - arXiv preprint arXiv …, 2022 - arxiv.org
Current keyword spotting systems are typically trained with a large amount of pre-defined
keywords. Recognizing keywords in an open-vocabulary setting is essential for …

Teaching keyword spotters to spot new keywords with limited examples

A Awasthi, K Kilgour, H Rom - arXiv preprint arXiv:2106.02443, 2021 - arxiv.org
Learning to recognize new keywords with just a few examples is essential for personalizing
keyword spotting (KWS) models to a user's choice of keywords. However, modern KWS …

Robust speech command recognition in challenging industrial environments

S Bini, V Carletti, A Saggese, M Vento - Computer Communications, 2024 - Elsevier
Speech is among the main forms of communication between humans and robots in
industrial settings, being the most natural way for a human worker to issue commands …

[PDF][PDF] Knowledge distillation for In-memory keyword spotting model.

Z Song, Q Liu, Q Yang, H Li - INTERSPEECH, 2022 - isca-archive.org
We study a light-weight implementation of keyword spotting (KWS) for voice command and
control, that can be implemented on an in-memory computing (IMC) unit with same accuracy …