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

Domain adaptation using text-only corpus is challenging in end-to-end(E2E)speech recognition. Adaptation by synthesizing audio from text through TTS isresource-consuming. We present a method to learn Unified Speech-TextRepresentation in Conformer Transducer(USTR-CT) to enable fast domainadaptation using the text-only corpus. Different from the previous textogrammethod, an extra text encoder is introduced in our work to learn textrepresentation and is removed during inference, so there is no modification foronline deployment. To improve the efficiency of adaptation, single-step andmulti-step adaptations are also explored. The experiments on adaptingLibriSpeech to SPGISpeech show the proposed method reduces the word errorrate(WER) by relatively 44% on the target domain, which is better than those ofTTS method and textogram method. Also, it is shown the proposed method can becombined with internal language model estimation(ILME) to further improve theperformance.

Text-only Domain Adaptation using Unified Speech-Text Representation in Transducer