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

This paper studies the task of speech reconstruction from ultrasound tongueimages and optical lip videos recorded in a silent speaking mode, where peopleonly activate their intra-oral and extra-oral articulators without producingsound. This task falls under the umbrella of articulatory-to-acousticconversion, and may also be refered to as a silent speech interface. We proposeto employ a method built on pseudo target generation and domain adversarialtraining with an iterative training strategy to improve the intelligibility andnaturalness of the speech recovered from silent tongue and lip articulation.Experiments show that our proposed method significantly improves theintelligibility and naturalness of the reconstructed speech in silent speakingmode compared to the baseline TaLNet model. When using an automatic speechrecognition (ASR) model to measure intelligibility, the word error rate (WER)of our proposed method decreases by over 15% compared to the baseline. Inaddition, our proposed method also outperforms the baseline on theintelligibility of the speech reconstructed in vocalized articulating mode,reducing the WER by approximately 10%.

Speech Reconstruction from Silent Tongue and Lip Articulation By Pseudo Target Generation and Domain Adversarial Training