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

In this paper, we present an end-to-end automatic speech recognition system,which successfully employs subword units in a hybrid CTC-Attention basedsystem. The subword units are obtained by the byte-pair encoding (BPE)compression algorithm. Compared to using words as modeling units, usingcharacters or subword units does not suffer from the out-of-vocabulary (OOV)problem. Furthermore, using subword units further offers a capability inmodeling longer context than using characters. We evaluate different systemsover the LibriSpeech 1000h dataset. The subword-based hybrid CTC-Attentionsystem obtains 6.8% word error rate (WER) on the test_clean subset without anydictionary or external language model. This represents a significantimprovement (a 12.8% WER relative reduction) over the character-based hybridCTC-Attention system.

Hybrid CTC-Attention based End-to-End Speech Recognition using Subword Units