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

Despite the feature of real-time decoding, Monotonic Multihead Attention(MMA) shows comparable performance to the state-of-the-art offline methods inmachine translation and automatic speech recognition (ASR) tasks. However, thelatency of MMA is still a major issue in ASR and should be combined with atechnique that can reduce the test latency at inference time, such ashead-synchronous beam search decoding, which forces all non-activated heads toactivate after a small fixed delay from the first head activation. In thispaper, we remove the discrepancy between training and test phases byconsidering, in the training of MMA, the interactions across multiple headsthat will occur in the test time. Specifically, we derive the expectedalignments from monotonic attention by considering the boundaries of otherheads and reflect them in the learning process. We validate our proposed methodon the two standard benchmark datasets for ASR and show that our approach, MMAwith the mutually-constrained heads from the training stage, provides betterperformance than baselines.

Mutually-Constrained Monotonic Multihead Attention for Online ASR