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

Acoustic word embeddings are typically created by training a pooling functionusing pairs of word-like units. For unsupervised systems, these are mined usingk-nearest neighbor (KNN) search, which is slow. Recently, mean-pooledrepresentations from a pre-trained self-supervised English model were suggestedas a promising alternative, but their performance on target languages was notfully competitive. Here, we explore improvements to both approaches: we usecontinued pre-training to adapt the self-supervised model to the targetlanguage, and we use a multilingual phone recognizer (MPR) to mine phone n-grampairs for training the pooling function. Evaluating on four languages, we showthat both methods outperform a recent approach on word discrimination.Moreover, the MPR method is orders of magnitude faster than KNN, and is highlydata efficient. We also show a small improvement from performing learnedpooling on top of the continued pre-trained representations.

Acoustic Word Embeddings for Untranscribed Target Languages with Continued Pretraining and Learned Pooling