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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

We train a MOS prediction model based on wav2vec 2.0 using the open-accessdata sets BVCC and SOMOS. Our test with neural TTS data in the low-resourcelanguage (LRL) West Frisian shows that pre-training on BVCC before fine-tuningon SOMOS leads to the best accuracy for both fine-tuned and zero-shotprediction. Further fine-tuning experiments show that using more than 30percent of the total data does not lead to significant improvements. Inaddition, fine-tuning with data from a single listener shows promisingsystem-level accuracy, supporting the viability of one-participant pilot tests.These findings can all assist the resource-conscious development of TTS forLRLs by progressing towards better zero-shot MOS prediction and informing thedesign of listening tests, especially in early-stage evaluation.

Resource-Efficient Fine-Tuning Strategies for Automatic MOS Prediction in Text-to-Speech for Low-Resource Languages