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

How do neural networks "perceive" speech sounds from unknown languages? Doesthe typological similarity between the model's training language (L1) and anunknown language (L2) have an impact on the model representations of L2 speechsignals? To answer these questions, we present a novel experimental designbased on representational similarity analysis (RSA) to analyze acoustic wordembeddings (AWEs) -- vector representations of variable-duration spoken-wordsegments. First, we train monolingual AWE models on seven Indo-Europeanlanguages with various degrees of typological similarity. We then employ RSA toquantify the cross-lingual similarity by simulating native and non-nativespoken-word processing using AWEs. Our experiments show that typologicalsimilarity indeed affects the representational similarity of the models in ourstudy. We further discuss the implications of our work on modeling speechprocessing and language similarity with neural networks.

How Familiar Does That Sound? Cross-Lingual Representational Similarity Analysis of Acoustic Word Embeddings