Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Danny Websdale"'
Publikováno v:
IEEE Transactions on Multimedia. 24:2539-2552
We propose a real-time speaker-independent speech-to-facial animation system that predicts lip and jaw movements on a reference face for audio speech taken from any speaker. Our approach is motivated by two key observations; 1) Speaker-independent fa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f6e2fd4605efb785218b93c94bfdb8f4
https://doi.org/10.1109/tmm.2021.3087020
https://doi.org/10.1109/tmm.2021.3087020
Autor:
Aaron Bostrom, Danny Websdale, Joshua Ball, Joshua Colmer, Rene Benjamins, Qiaojun Lou, Gema Flores Andaluz, Gagan Shiralagi, Ji Zhou, Daniel Reynolds, Steven Penfield, Wei Lu, Carmel M. O’Neill, Thomas Le Cornu, Jim Renema, Rachel Wells
Publikováno v:
New Phytologist. 228:778-793
Efficient seed germination and establishment are important traits for field and glasshouse crops. Large-scale germination experiments are laborious and prone to observer errors, leading to the necessity for automated methods. We experimented with fiv
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8a392b674accfbfe7f9034d134c7aff6
https://doi.org/10.1111/nph.16736
https://doi.org/10.1111/nph.16736
Publikováno v:
INTERSPEECH
Machine learning has previously been applied successfully to speech-driven facial animation. To account for carry-over and anticipatory coarticulation a common approach is to predict the facial pose using a symmetric window of acoustic speech that in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6bf0009f8b49e15c600726940afd82a2
https://ueaeprints.uea.ac.uk/id/eprint/71940/
https://ueaeprints.uea.ac.uk/id/eprint/71940/
Using visual speech information and perceptually motivated loss functions for binary mask estimation
Autor:
Danny Websdale, Ben Milner
Publikováno v:
AVSP
This work is concerned with using deep neural networks for estimating binary masks within a speech enhancement framework. We first examine the effect of supplementing the audio features used in mask estimation with visual speech information. Visual s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1c0df762c7879ec919d0d44d175f337b
https://doi.org/10.21437/avsp.2017-9
https://doi.org/10.21437/avsp.2017-9
Autor:
Danny Websdale, Ben Milner
Publikováno v:
INTERSPEECH
This work proposes and compares perceptually motivated loss functions for deep learning based binary mask estimation for speech separation. Previous loss functions have focused on maximising classification accuracy of mask estimation but we now propo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6ae87c3d2662f72a5b6a08c4d6007cd2
https://doi.org/10.21437/interspeech.2017-1504
https://doi.org/10.21437/interspeech.2017-1504
Autor:
Clark, Finlayson G, Ji Zhou, Michael W. Bevan, Simon Griffiths, Danny Websdale, Clare Lister, Daniel Reynolds, Simon Orford, Thomas Le Cornu, Gonzalez-Navarro O, Stephen D. Laycock, Stitt T
Automated phenotyping technologies are capable of providing continuous and precise measurements of traits that are key to today’s crop research, breeding and agronomic practices. In additional to monitoring developmental changes, high-frequency and
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4377baa4589bd6aeb980fed67f1a903b
Publikováno v:
INTERSPEECH
A study is presented on how well objective measures of speech quality and intelligibility can predict the subjective in- telligibility of speech that has undergone spectral envelope smoothing and simplification of its excitation. Speech modi- ficatio
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::83ccc7b473ffd7d364ed976f5064aee8
https://ueaeprints.uea.ac.uk/id/eprint/55879/
https://ueaeprints.uea.ac.uk/id/eprint/55879/