English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Despite showing state-of-the-art performance, deep learning for speechrecognition remains challenging to deploy in on-device edge scenarios such asmobile and other consumer devices. Recently, there have been greater efforts inthe design of small, low-footprint deep neural networks (DNNs) that are moreappropriate for edge devices, with much of the focus on design principles forhand-crafting efficient network architectures. In this study, we explore ahuman-machine collaborative design strategy for building low-footprint DNNarchitectures for speech recognition through a marriage of human-drivenprincipled network design prototyping and machine-driven design exploration.The efficacy of this design strategy is demonstrated through the design of afamily of highly-efficient DNNs (nicknamed EdgeSpeechNets) forlimited-vocabulary speech recognition. Experimental results using the GoogleSpeech Commands dataset for limited-vocabulary speech recognition showed thatEdgeSpeechNets have higher accuracies than state-of-the-art DNNs (with the bestEdgeSpeechNet achieving ~97% accuracy), while achieving significantly smallernetwork sizes (as much as 7.8x smaller) and lower computational cost (as muchas 36x fewer multiply-add operations, 10x lower prediction latency, and 16xsmaller memory footprint on a Motorola Moto E phone), making them verywell-suited for on-device edge voice interface applications.

EdgeSpeechNets: Highly Efficient Deep Neural Networks for Speech Recognition on the Edge