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 recent advancements in deep learning technologies, Child SpeechRecognition remains a challenging task. Current Automatic Speech Recognition(ASR) models require substantial amounts of annotated data for training, whichis scarce. In this work, we explore using the ASR model, wav2vec2, withdifferent pretraining and finetuning configurations for self-supervisedlearning (SSL) toward improving automatic child speech recognition. Thepretrained wav2vec2 models were finetuned using different amounts of childspeech training data, adult speech data, and a combination of both, to discoverthe optimum amount of data required to finetune the model for the task of childASR. Our trained model achieves the best Word Error Rate (WER) of 7.42 on theMyST child speech dataset, 2.99 on the PFSTAR dataset and 12.47 on the CMU KIDSdataset as compared to any other previous methods. Our models outperformed thewav2vec2 BASE 960 on child speech which is considered a state-of-the-art ASRmodel on adult speech by just using 10 hours of child speech data infinetuning. The analysis of different types of training data and their effecton inference is also provided by using a combination of datasets inpretraining, finetuning and inference.

A Wav2vec2-Based Experimental Study on Self-Supervised Learning Methods to Improve Child Speech Recognition