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 for young children are needed dueto the importance of age-appropriate educational technology. Because of thelack of publicly available young child speech data, feature extractionstrategies such as feature normalization and data augmentation must beconsidered to successfully train child ASR systems. This study proposes a noveltechnique for child ASR using both feature normalization and data augmentationmethods based on the relationship between formants and fundamental frequency($f_o$). Both the $f_o$ feature normalization and data augmentation techniquesare implemented as a frequency shift in the Mel domain. These techniques areevaluated on a child read speech ASR task. Child ASR systems are trained byadapting a BLSTM-based acoustic model trained on adult speech. Using both $f_o$normalization and data augmentation results in a relative word error rate (WER)improvement of 19.3% over the baseline when tested on the OGI Kids' SpeechCorpus, and the resulting child ASR system achieves the best WER currentlyreported on this corpus.

Fundamental Frequency Feature Normalization and Data Augmentation for Child Speech Recognition