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

End-to-end models are favored in automatic speech recognition (ASR) becauseof its simplified system structure and superior performance. Among thesemodels, recurrent neural network transducer (RNN-T) has achieved significantprogress in streaming on-device speech recognition because of its high-accuracyand low-latency. RNN-T adopts a prediction network to enhance languageinformation, but its language modeling ability is limited because it stillneeds paired speech-text data to train. Further strengthening the languagemodeling ability through extra text data, such as shallow fusion with anexternal language model, only brings a small performance gain. In view of thefact that Mandarin Chinese is a character-based language and each character ispronounced as a tonal syllable, this paper proposes a novel cascade RNN-Tapproach to improve the language modeling ability of RNN-T. Our approachfirstly uses an RNN-T to transform acoustic feature into syllable sequence, andthen converts the syllable sequence into character sequence through anRNN-T-based syllable-to-character converter. Thus a rich text repository can beeasily used to strengthen the language model ability. By introducing severalimportant tricks, the cascade RNN-T approach surpasses the character-basedRNN-T by a large margin on several Mandarin test sets, with much higherrecognition quality and similar latency.

Cascade RNN-Transducer: Syllable Based Streaming On-device Mandarin Speech Recognition with a Syllable-to-Character Converter