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

We describe a comprehensive methodology for developing user-voicepersonalized automatic speech recognition (ASR) models by effectively trainingmodels on mobile phones, allowing user data and models to be stored and usedlocally. To achieve this, we propose a resource-aware sub-model-based trainingapproach that considers the RAM, and battery capabilities of mobile phones. Byconsidering the evaluation metric and resource constraints of the mobilephones, we are able to perform efficient training and halt the processaccordingly. To simulate real users, we use speakers with various accents. Theentire on-device training and evaluation framework was then tested on variousmobile phones across brands. We show that fine-tuning the models and selectingthe right hyperparameter values is a trade-off between the lowest achievableperformance metric, on-device training time, and memory consumption. Overall,our methodology offers a comprehensive solution for developing personalized ASRmodels while leveraging the capabilities of mobile phones, and balancing theneed for accuracy with resource constraints.

MobileASR: A resource-aware on-device learning framework for user voice personalization applications on mobile phones