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

Speech signals, typically sampled at rates in the tens of thousands persecond, contain redundancies, evoking inefficiencies in sequence modeling.High-dimensional speech features such as spectrograms are often used as theinput for the subsequent model. However, they can still be redundant. Recentinvestigations proposed the use of discrete speech units derived fromself-supervised learning representations, which significantly compresses thesize of speech data. Applying various methods, such as de-duplication andsubword modeling, can further compress the speech sequence length. Hence,training time is significantly reduced while retaining notable performance. Inthis study, we undertake a comprehensive and systematic exploration into theapplication of discrete units within end-to-end speech processing models.Experiments on 12 automatic speech recognition, 3 speech translation, and 1spoken language understanding corpora demonstrate that discrete units achievereasonably good results in almost all the settings. We intend to release ourconfigurations and trained models to foster future research efforts.

Exploring Speech Recognition, Translation, and Understanding with Discrete Speech Units: A Comparative Study