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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Multilingual self-supervised speech representation models have greatlyenhanced the speech recognition performance for low-resource languages, and thecompression of these huge models has also become a crucial prerequisite fortheir industrial application. In this paper, we propose DistilXLSR, a distilledcross-lingual speech representation model. By randomly shuffling the phonemesof existing speech, we reduce the linguistic information and distillcross-lingual models using only English data. We also design a layer-jumpinginitialization method to fully leverage the teacher's pre-trained weights.Experiments on 2 kinds of teacher models and 15 low-resource languages showthat our method can reduce the parameters by 50% while maintainingcross-lingual representation ability. Our method is proven to be generalizableto various languages/teacher models and has the potential to improve thecross-lingual performance of the English pre-trained models.

DistilXLSR: A Light Weight Cross-Lingual Speech Representation Model