Micron Document




LipNet
──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
top
LipNet is a deep neural network for audio-visual speech recognition (ASVR). It was created by University of Oxford researchers Yannis Assael, Brendan Shillingford, Shimon Whiteson, and Nando de Freitas.cite-ref-1[1] Audio-visual speech recognition has enormous practical potential, with applications such as improved hearing aids, improving the recovery and wellbeing of critically ill patients,cite-ref-2[2] and speech recognition in noisy environments,cite-ref-3[3] implemented for example in Nvidia's autonomous vehicles.cite-ref-4[4]

References

cite-note-11. citerefassaelshillingfordwhitesonde-freitas2016Assael, Yannis M.; Shillingford, Brendan; Whiteson, Shimon; de Freitas, Nando (2016-12-16). "LipNet: End-to-End Sentence-level Lipreading". arXiv:1611.01599 [cs.LG].
cite-note-22. "Home Elementor". Liopa.
cite-note-33. citerefvincent2016Vincent, James (November 7, 2016). "Can deep learning help solve lip reading?". The Verge.
cite-note-44. citerefquachQuach, Katyanna. "Revealed: How Nvidia's 'backseat driver' AI learned to read lips". www.theregister.com.