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

Automatic Speech Recognition (ASR) systems have found their use in numerousindustrial applications in very diverse domains creating a need to adapt to newdomains with small memory and deployment overhead. In this work, we introducedomain-prompts, a methodology that involves training a small number of domainembedding parameters to prime a Transformer-based Language Model (LM) to aparticular domain. Using this domain-adapted LM for rescoring ASR hypothesescan achieve 7-13% WER reduction for a new domain with just 1000 unlabeledtextual domain-specific sentences. This improvement is comparable or evenbetter than fully fine-tuned models even though just 0.02% of the parameters ofthe base LM are updated. Additionally, our method is deployment-friendly as thelearnt domain embeddings are prefixed to the input to the model rather thanchanging the base model architecture. Therefore, our method is an ideal choicefor on-the-fly adaptation of LMs used in ASR systems to progressively scale itto new domains.

Prompt Tuning GPT-2 language model for parameter-efficient domain adaptation of ASR systems