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

The recent emergence of joint CTC-Attention model shows significantimprovement in automatic speech recognition (ASR). The improvement largely liesin the modeling of linguistic information by decoder. The decoderjoint-optimized with an acoustic encoder renders the language model fromground-truth sequences in an auto-regressive manner during training. However,the training corpus of the decoder is limited to the speech transcriptions,which is far less than the corpus needed to train an acceptable language model.This leads to poor robustness of decoder. To alleviate this problem, we proposelinguistic-enhanced transformer, which introduces refined CTC information todecoder during training process, so that the decoder can be more robust. Ourexperiments on AISHELL-1 speech corpus show that the character error rate (CER)is relatively reduced by up to 7%. We also find that in joint CTC-Attention ASRmodel, decoder is more sensitive to linguistic information than acousticinformation.

Linguistic-Enhanced Transformer with CTC Embedding for Speech Recognition