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

Recent studies on pronunciation scoring have explored the effect ofintroducing phone embeddings as reference pronunciation, but mostly in animplicit manner, i.e., addition or concatenation of reference phone embeddingand actual pronunciation of the target phone as the phone-level pronunciationquality representation. In this paper, we propose to use linguistic-acousticsimilarity to explicitly measure the deviation of non-native production fromits native reference for pronunciation assessment. Specifically, the deviationis first estimated by the cosine similarity between reference phone embeddingand corresponding acoustic embedding. Next, a phone-level Goodness ofpronunciation (GOP) pre-training stage is introduced to guide thissimilarity-based learning for better initialization of the aforementioned twoembeddings. Finally, a transformer-based hierarchical pronunciation scorer isused to map a sequence of phone embeddings, acoustic embeddings along withtheir similarity measures to predict the final utterance-level score.Experimental results on the non-native databases suggest that the proposedsystem significantly outperforms the baselines, where the acoustic and phoneembeddings are simply added or concatenated. A further examination shows thatthe phone embeddings learned in the proposed approach are able to capturelinguistic-acoustic attributes of native pronunciation as reference.

Leveraging phone-level linguistic-acoustic similarity for utterance-level pronunciation scoring