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

We propose a method for zero-resource domain adaptation of DNN acousticmodels, for use in low-resource situations where the only in-language trainingdata available may be poorly matched to the intended target domain. Our methoduses a multi-lingual model in which several DNN layers are shared betweenlanguages. This architecture enables domain adaptation transforms learned forone well-resourced language to be applied to an entirely different low-resourcelanguage. First, to develop the technique we use English as a well-resourcedlanguage and take Spanish to mimic a low-resource language. Experiments indomain adaptation between the conversational telephone speech (CTS) domain andbroadcast news (BN) domain demonstrate a 29% relative WER improvement onSpanish BN test data by using only English adaptation data. Second, wedemonstrate the effectiveness of the method for low-resource languages with apoor match to the well-resourced language. Even in this scenario, the proposedmethod achieves relative WER improvements of 18-27% by using solely Englishdata for domain adaptation. Compared to other related approaches based onmulti-task and multi-condition training, the proposed method is able to betterexploit well-resource language data for improved acoustic modelling of thelow-resource target domain.

Cross lingual transfer learning for zero-resource domain adaptation