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

Speech synthesis technology has witnessed significant advancements in recentyears, enabling the creation of natural and expressive synthetic speech. Onearea of particular interest is the generation of synthetic child speech, whichpresents unique challenges due to children's distinct vocal characteristics anddevelopmental stages. This paper presents a novel approach that leverages theFastpitch text-to-speech (TTS) model for generating high-quality syntheticchild speech. This study uses the transfer learning training pipeline. Theapproach involved finetuning a multi-speaker TTS model to work with childspeech. We use the cleaned version of the publicly available MyST dataset (55hours) for our finetuning experiments. We also release a prototype dataset ofsynthetic speech samples generated from this research together with model codeto support further research. By using a pretrained MOSNet, we conducted anobjective assessment that showed a significant correlation between real andsynthetic child voices. Additionally, to validate the intelligibility of thegenerated speech, we employed an automatic speech recognition (ASR) model tocompare the word error rates (WER) of real and synthetic child voices. Thespeaker similarity between the real and generated speech is also measured usinga pretrained speaker encoder.

Improved Child Text-to-Speech Synthesis through Fastpitch-based Transfer Learning