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/

Zendy Plus

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

Zendy Tools

Zendy Open

Modern automatic speaker verification relies largely on deep neural networks(DNNs) trained on mel-frequency cepstral coefficient (MFCC) features. Whilethere are alternative feature extraction methods based on phase, prosody andlong-term temporal operations, they have not been extensively studied withDNN-based methods. We aim to fill this gap by providing extensive re-assessmentof 14 feature extractors on VoxCeleb and SITW datasets. Our findings revealthat features equipped with techniques such as spectral centroids, group delayfunction, and integrated noise suppression provide promising alternatives toMFCCs for deep speaker embeddings extraction. Experimental results demonstrateup to 16.3\% (VoxCeleb) and 25.1\% (SITW) relative decrease in equal error rate(EER) to the baseline.

A Comparative Re-Assessment of Feature Extractors for Deep Speaker Embeddings