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

Unsupervised segmentation and clustering of unlabelled speech are coreproblems in zero-resource speech processing. Most approaches lie atmethodological extremes: some use probabilistic Bayesian models withconvergence guarantees, while others opt for more efficient heuristictechniques. Despite competitive performance in previous work, the full Bayesianapproach is difficult to scale to large speech corpora. We introduce anapproximation to a recent Bayesian model that still has a clear objectivefunction but improves efficiency by using hard clustering and segmentationrather than full Bayesian inference. Like its Bayesian counterpart, thisembedded segmental K-means model (ES-KMeans) represents arbitrary-length wordsegments as fixed-dimensional acoustic word embeddings. We first compareES-KMeans to previous approaches on common English and Xitsonga data sets (5and 2.5 hours of speech): ES-KMeans outperforms a leading heuristic method inword segmentation, giving similar scores to the Bayesian model while being 5times faster with fewer hyperparameters. However, its clusters are less purethan those of the other models. We then show that ES-KMeans scales to largercorpora by applying it to the 5 languages of the Zero Resource Speech Challenge2017 (up to 45 hours), where it performs competitively compared to thechallenge baseline.

An embedded segmental K-means model for unsupervised segmentation and clustering of speech