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

Automatic speech recognition (ASR) has been widely researched with supervisedapproaches, while many low-resourced languages lack audio-text aligned data,and supervised methods cannot be applied on them.  In this work, we propose a framework to achieve unsupervised ASR on a readEnglish speech dataset, where audio and text are unaligned. In the first stage,each word-level audio segment in the utterances is represented by a vectorrepresentation extracted by a sequence-of-sequence autoencoder, in whichphonetic information and speaker information are disentangled.  Secondly, semantic embeddings of audio segments are trained from the vectorrepresentations using a skip-gram model. Last but not the least, anunsupervised method is utilized to transform semantic embeddings of audiosegments to text embedding space, and finally the transformed embeddings aremapped to words.  With the above framework, we are towards unsupervised ASR trained byunaligned text and speech only.

Towards Unsupervised Automatic Speech Recognition Trained by Unaligned Speech and Text only