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

In this work, we analyzed and compared speech representations extracted fromdifferent frozen self-supervised learning (SSL) speech pre-trained models ontheir ability to capture articulatory features (AF) information and theirsubsequent prediction of phone recognition performance for within and acrosslanguage scenarios. Specifically, we compared CPC, wav2vec 2.0, and HuBert.First, frame-level AF probing tasks were implemented. Subsequently, phone-levelend-to-end ASR systems for phoneme recognition tasks were implemented, and theperformance on the frame-level AF probing task and the phone accuracy werecorrelated. Compared to the conventional speech representation MFCC, all SSLpre-trained speech representations captured more AF information, and achievedbetter phoneme recognition performance within and across languages, with HuBertperforming best. The frame-level AF probing task is a good predictor of phonemerecognition performance, showing the importance of capturing AF information inthe speech representations. Compared with MFCC, in the within-languagescenario, the performance of these SSL speech pre-trained models on AF probingtasks achieved a maximum relative increase of 34.4%, and it resulted in thelowest PER of 10.2%. In the cross-language scenario, the maximum relativeincrease of 26.7% also resulted in the lowest PER of 23.0%.

Predicting within and across language phoneme recognition performance of self-supervised learning speech pre-trained models