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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Phonotactic constraints can be employed to distinguish languages byrepresenting a speech utterance as a multinomial distribution or phone events.In the present study, we propose a new learning mechanism based onsubspace-based representation, which can extract concealed phonotacticstructures from utterances, for language verification and dialect/accentidentification. The framework mainly involves two successive parts. The firstpart involves subspace construction. Specifically, it decodes each utteranceinto a sequence of vectors filled with phone-posteriors and transforms thevector sequence into a linear orthogonal subspace based on low-rank matrixfactorization or dynamic linear modeling. The second part involves subspacelearning based on kernel machines, such as support vector machines and thenewly developed subspace-based neural networks (SNNs). The input layer of SNNsis specifically designed for the sample represented by subspaces. The topologyensures that the same output can be derived from identical subspaces bymodifying the conventional feed-forward pass to fit the mathematical definitionof subspace similarity. Evaluated on the "General LR" test of NIST LRE 2007,the proposed method achieved up to 52%, 46%, 56%, and 27% relative reductionsin equal error rates over the sequence-based PPR-LM, PPR-VSM, and PPR-IVECmethods and the lattice-based PPR-LM method, respectively. Furthermore, on thedialect/accent identification task of NIST LRE 2009, the SNN-based systemperformed better than the aforementioned four baseline methods.

Subspace-based Representation and Learning for Phonotactic Spoken Language Recognition