Deep word embeddings for visual speech recognition
Autori:
Stafylakis, Themos; Tzimiropoulos, Georgios
Pubblicato in:
IEEE International Conference on Acoustics, Speech, and Signal Processing, 2018
Editore:
IEEE
End-to-end Audiovisual Speech Recognition
Autori:
Stavros Petridis, Themos Stafylakis, Pingchuan Ma, Feipeng Cai, Georgios Tzimiropoulos, Maja Pantic
Pubblicato in:
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018
Editore:
IEEE
Combining Residual Networks with LSTMs for Lipreading
Autori:
Themos Stafylakis, Georgios Tzimiropoulos
Pubblicato in:
Interspeech, 2017
Editore:
ISCA
Gaussian meta-embeddings for efficient scoring of a heavy-tailed PLDA model
Autori:
Brummer, Niko; Silnova, Anna; Burget, Lukas; Stafylakis, Themos
Pubblicato in:
Proceedings of Odyssey, 2018
Editore:
ISCA
The I4U mega fusion and collaboration for NIST speaker recognition evaluation 2016
Autori:
Kong-Aik Lee, Ville Hautamäki, Tomi Kinnunen, Anthony Larcher, C Zhang, A Nautsch, T Stafylakis, G Liu, M Rouvier, W Rao, F Alegre, J Ma, MW Mak, AK Sarkar, H Delgado, R Saeidi, H Aronowitz, A Sizov, H Sun, TH Nguyen, Md Sahidullah, V Vestman, M Halonen, A Kanervisto
Pubblicato in:
Interspeech, 2017
Editore:
ISCA
Zero-shot keyword spotting for visual speech recognition in-the-wild
Autori:
Themos Stafylakis, Georgios Tzimiropoulos
Pubblicato in:
European Conference on Computer Vision (ECCV), 2018
Editore:
The Computer Vision Foundation
The I4U submission to the 2016 NIST speaker recognition evaluation
Autori:
Kong-Aik Lee, Ville Hautamäki, Tomi Kinnunen, Anthony Larcher, C Zhang, A Nautsch, T Stafylakis, G Liu, M Rouvier, W Rao, F Alegre, J Ma, MW Mak, AK Sarkar, H Delgado, R Saeidi, H Aronowitz, A Sizov, H Sun, TH Nguyen, Md Sahidullah, V Vestman, M Halonen, A Kanervisto
Pubblicato in:
NIST SRE 2016 Workshop, 2016
Editore:
NIST
