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

Spoken term discovery from untranscribed speech audio could be achieved via atwo-stage process. In the first stage, the unlabelled speech is decoded into asequence of subword units that are learned and modelled in an unsupervisedmanner. In the second stage, partial sequence matching and clustering areperformed on the decoded subword sequences, resulting in a set of discoveredwords or phrases. A limitation of this approach is that the results of subworddecoding could be erroneous, and the errors would impact the subsequent steps.While Siamese/Triplet network is one approach to learn segment representationsthat can improve the discovery process, the challenge in spoken term discoveryunder a complete unsupervised scenario is that training examples areunavailable. In this paper, we propose to generate training examples frominitial hypothesized sequence clusters. The Siamese/Triplet network is trainedon the hypothesized examples to measure the similarity between two speechsegments and hereby perform re-clustering of all hypothesized subword sequencesto achieve spoken term discovery. Experimental results show that the proposedapproach is effective in obtaining training examples for Siamese and Tripletnetworks, improving the efficacy of spoken term discovery as compared with theoriginal two-stage method.

Unsupervised Spoken Term Discovery Based on Re-clustering of Hypothesized Speech Segments with Siamese and Triplet Networks