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

Automatic Speech Recognition (ASR) systems have progressed significantly intheir performance on adult speech data; however, transcribing child speechremains challenging due to the acoustic differences in the characteristics ofchild and adult voices. This work aims to explore the potential of adaptingstate-of-the-art Conformer-transducer models to child speech to improve childspeech recognition performance. Furthermore, the results are compared withthose of self-supervised wav2vec2 models and semi-supervised multi-domainWhisper models that were previously finetuned on the same data. We demonstratethat finetuning Conformer-transducer models on child speech yields significantimprovements in ASR performance on child speech, compared to the non-finetunedmodels. We also show Whisper and wav2vec2 adaptation on different child speechdatasets. Our detailed comparative analysis shows that wav2vec2 provides themost consistent performance improvements among the three methods studied.

A comparative analysis between Conformer-Transducer, Whisper, and wav2vec2 for improving the child speech recognition