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

Recently, direct modeling of raw waveforms using deep neural networks hasbeen widely studied for a number of tasks in audio domains. In speakerverification, however, utilization of raw waveforms is in its preliminaryphase, requiring further investigation. In this study, we explore end-to-enddeep neural networks that input raw waveforms to improve various aspects:front-end speaker embedding extraction including model architecture,pre-training scheme, additional objective functions, and back-endclassification. Adjustment of model architecture using a pre-training schemecan extract speaker embeddings, giving a significant improvement inperformance. Additional objective functions simplify the process of extractingspeaker embeddings by merging conventional two-phase processes: extractingutterance-level features such as i-vectors or x-vectors and the featureenhancement phase, e.g., linear discriminant analysis. Effective back-endclassification models that suit the proposed speaker embedding are alsoexplored. We propose an end-to-end system that comprises two deep neuralnetworks, one front-end for utterance-level speaker embedding extraction andthe other for back-end classification. Experiments conducted on the VoxCeleb1dataset demonstrate that the proposed model achieves state-of-the-artperformance among systems without data augmentation. The proposed system isalso comparable to the state-of-the-art x-vector system that adopts dataaugmentation.

RawNet: Advanced end-to-end deep neural network using raw waveforms for text-independent speaker verification