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

Estimation of a speaker's direction and head orientation with binauralrecordings can be a critical piece of information in many real-worldapplications with emerging `earable' devices, including smart headphones andAR/VR headsets. However, it requires predicting the mutual head orientations ofboth the speaker and the listener, which is challenging in practice. This paperpresents a system for jointly predicting speaker-listener head orientations byleveraging inherent human voice directivity and listener's head-relatedtransfer function (HRTF) as perceived by the ear-mounted microphones on thelistener. We propose a convolution neural network model that, given binauralspeech recording, can predict the orientation of both speaker and listener withrespect to the line joining the two. The system builds on the core observationthat the recordings from the left and right ears are differentially affected bythe voice directivity as well as the HRTF. We also incorporate the fact thatvoice is more directional at higher frequencies compared to lower frequencies.

Simultaneously Learning Speaker's Direction and Head Orientation from Binaural Recordings