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

TV subtitles are a rich source of transcriptions of many types of speech,ranging from read speech in news reports to conversational and spontaneousspeech in talk shows and soaps. However, subtitles are not verbatim (i.e.exact) transcriptions of speech, so they cannot be used directly to improve anAutomatic Speech Recognition (ASR) model. We propose a multitask dual-decoderTransformer model that jointly performs ASR and automatic subtitling. The ASRdecoder (possibly pre-trained) predicts the verbatim output and the subtitledecoder generates a subtitle, while sharing the encoder. The two decoders canbe independent or connected. The model is trained to perform both tasksjointly, and is able to effectively use subtitle data. We show improvements onregular ASR and on spontaneous and conversational ASR by incorporating theadditional subtitle decoder. The method does not require preprocessing(aligning, filtering, pseudo-labeling, ...) of the subtitles.

Learning to Jointly Transcribe and Subtitle for End-to-End Spontaneous Speech Recognition