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

Audio Word2Vec offers vector representations of fixed dimensionality forvariable-length audio segments using Sequence-to-sequence Autoencoder (SA).These vector representations are shown to describe the sequential phoneticstructures of the audio segments to a good degree, with real world applicationssuch as query-by-example Spoken Term Detection (STD). This paper examines thecapability of language transfer of Audio Word2Vec. We train SA from onelanguage (source language) and use it to extract the vector representation ofthe audio segments of another language (target language). We found that SA canstill catch phonetic structure from the audio segments of the target languageif the source and target languages are similar. In query-by-example STD, weobtain the vector representations from the SA learned from a large amount ofsource language data, and found them surpass the representations from naiveencoder and SA directly learned from a small amount of target language data.The result shows that it is possible to learn Audio Word2Vec model fromhigh-resource languages and use it on low-resource languages. This furtherexpands the usability of Audio Word2Vec.

Language Transfer of Audio Word2Vec: Learning Audio Segment Representations without Target Language Data