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

In this paper, we provide a series of multi-tasking benchmarks forsimultaneously detecting spoofing at the segmental and utterance levels in thePartialSpoof database. First, we propose the SELCNN network, which insertssqueeze-and-excitation (SE) blocks into a light convolutional neural network(LCNN) to enhance the capacity of hidden feature selection. Then, we implementmulti-task learning (MTL) frameworks with SELCNN followed by bidirectional longshort-term memory (Bi-LSTM) as the basic model. We discuss MTL in PartialSpoofin terms of architecture (uni-branch/multi-branch) and training strategies(from-scratch/warm-up) step-by-step. Experiments show that the multi-task modelperforms relatively better than single-task models. Also, in MTL, abinary-branch architecture more adequately utilizes information from two levelsthan a uni-branch model. For the binary-branch architecture, fine-tuning awarm-up model works better than training from scratch. Models can handle bothsegment-level and utterance-level predictions simultaneously overall under abinary-branch multi-task architecture. Furthermore, the multi-task modeltrained by fine-tuning a segmental warm-up model performs relatively better atboth levels except on the evaluation set for segmental detection. Segmentaldetection should be explored further.

Multi-Task Learning in Utterance-Level and Segmental-Level Spoof Detection