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

Disfluency, though originating from human spoken utterances, is primarilystudied as a uni-modal text-based Natural Language Processing (NLP) task. Basedon early-fusion and self-attention-based multimodal interaction between textand acoustic modalities, in this paper, we propose a novel multimodalarchitecture for disfluency detection from individual utterances. Ourarchitecture leverages a multimodal dynamic fusion network that adds minimalparameters over an existing text encoder commonly used in prior art to leveragethe prosodic and acoustic cues hidden in speech. Through experiments, we showthat our proposed model achieves state-of-the-art results on the widely usedEnglish Switchboard for disfluency detection and outperforms prior unimodal andmultimodal systems in literature by a significant margin. In addition, we makea thorough qualitative analysis and show that, unlike text-only systems, whichsuffer from spurious correlations in the data, our system overcomes thisproblem through additional cues from speech signals. We make all our codespublicly available on GitHub.

A novel multimodal dynamic fusion network for disfluency detection in spoken utterances