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

Large self-supervised models are effective feature extractors, but theirapplication is challenging under on-device budget constraints and biaseddataset collection, especially in keyword spotting. To address this, weproposed a knowledge distillation-based self-supervised speech representationlearning (S3RL) architecture for on-device keyword spotting. Our approach useda teacher-student framework to transfer knowledge from a larger, more complexmodel to a smaller, light-weight model using dual-view cross-correlationdistillation and the teacher's codebook as learning objectives. We evaluatedour model's performance on an Alexa keyword spotting detection task using a16.6k-hour in-house dataset. Our technique showed exceptional performance innormal and noisy conditions, demonstrating the efficacy of knowledgedistillation methods in constructing self-supervised models for keywordspotting tasks while working within on-device resource constraints.

On-Device Constrained Self-Supervised Speech Representation Learning for Keyword Spotting via Knowledge Distillation