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

Audio-visual speech recognition (AVSR) gains increasing attention fromresearchers as an important part of human-computer interaction. However, theexisting available Mandarin audio-visual datasets are limited and lack thedepth information. To address this issue, this work establishes the MAVD, a newlarge-scale Mandarin multimodal corpus comprising 12,484 utterances spoken by64 native Chinese speakers. To ensure the dataset covers diverse real-worldscenarios, a pipeline for cleaning and filtering the raw text material has beendeveloped to create a well-balanced reading material. In particular, the latestdata acquisition device of Microsoft, Azure Kinect is used to capture depthinformation in addition to the traditional audio signals and RGB images duringdata acquisition. We also provide a baseline experiment, which could be used toevaluate the effectiveness of the dataset. The dataset and code will bereleased at https://github.com/SpringHuo/MAVD.

MAVD: The First Open Large-Scale Mandarin Audio-Visual Dataset with Depth Information