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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

(Part of the abstract) In this thesis, we investigate the use of unsupervisedspoken term discovery in tackling this problem. Unsupervised spoken termdiscovery aims to discover topic-related terminologies in a speech withoutknowing the phonetic properties of the language and content. It can be furtherdivided into two parts: Acoustic segment modelling (ASM) and unsupervisedpattern discovery. ASM learns the phonetic structures of zero-resource languageaudio with no phonetic knowledge available, generating self-derived "phonemes".The audio are labelled with these "phonemes" to obtain "phoneme" sequences.Unsupervised pattern discovery searches for repetitive patterns in the"phoneme" sequences. The discovered patterns can be grouped to determine thekeywords of the audio. Multilingual neural network with bottleneck layer isused for feature extraction. Experiments show that bottleneck featuresfacilitate the training of ASM compared to conventional features such as MFCC.The unsupervised spoken term discovery system is experimented with onlinelectures covering different topics by different speakers. It is shown that thesystem learns the phonetic information of the language and can discoverfrequent spoken terms that align with text transcription. By using informationretrieval technology such as word embedding and TFIDF, it is shown that thediscovered keywords can be further used for topic comparison.

Unsupervised Spoken Term Discovery on Untranscribed Speech