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

To extract accurate speaker information for text-independent speakerverification, temporal dynamic CNNs (TDY-CNNs) adapting kernels to each timebin was proposed. However, model size of TDY-CNN is too large and the adaptivekernel's degree of freedom is limited. To address these limitations, we proposedecomposed temporal dynamic CNNs (DTDY-CNNs) which forms time-adaptive kernelby combining static kernel with dynamic residual based on matrix decomposition.Proposed DTDY-ResNet-34(x0.50) using attentive statistical pooling without dataaugmentation shows EER of 0.96%, which is better than other state-of-the-artmethods. DTDY-CNNs are successful upgrade of TDY-CNNs, reducing the model sizeby 64% and enhancing the performance. We showed that DTDY-CNNs extract moreaccurate frame-level speaker embeddings as well compared to TDY-CNNs. Detailedbehaviors of DTDY-ResNet-34(x0.50) on extraction of speaker information wereanalyzed using speaker activation map (SAM) produced by modifiedgradient-weighted class activation mapping (Grad-CAM) for speaker verification.DTDY-ResNet-34(x0.50) effectively extracts speaker information from not onlyformant frequencies but also high frequency information of unvoiced phonemes,thus explaining its outstanding performance on text-independent speakerverification.

Decomposed Temporal Dynamic CNN: Efficient Time-Adaptive Network for Text-Independent Speaker Verification Explained with Speaker Activation Map