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 is the most used communication method between humans and it involvesthe perception of auditory and visual channels. Automatic speech recognitionfocuses on interpreting the audio signals, although the video can provideinformation that is complementary to the audio. Exploiting the visualinformation, however, has proven challenging. On one hand, researchers havereported that the mapping between phonemes and visemes (visual units) isone-to-many because there are phonemes which are visually similar andindistinguishable between them. On the other hand, it is known that some peopleare very good lip-readers (e.g: deaf people). We study the limit of visual onlyspeech recognition in controlled conditions. With this goal, we designed a newdatabase in which the speakers are aware of being read and aim to facilitatelip-reading. In the literature, there are discrepancies on whetherhearing-impaired people are better lip-readers than normal-hearing people.Then, we analyze if there are differences between the lip-reading abilities of9 hearing-impaired and 15 normal-hearing people. Finally, human abilities arecompared with the performance of a visual automatic speech recognition system.In our tests, hearing-impaired participants outperformed the normal-hearingparticipants but without reaching statistical significance. Human observerswere able to decode 44% of the spoken message. In contrast, the visual onlyautomatic system achieved 20% of word recognition rate. However, if we repeatthe comparison in terms of phonemes both obtained very similar recognitionrates, just above 50%. This suggests that the gap between human lip-reading andautomatic speech-reading might be more related to the use of context than tothe ability to interpret mouth appearance.

Towards Estimating the Upper Bound of Visual-Speech Recognition: The Visual Lip-Reading Feasibility Database