Publications

Publications 2020-07-29T17:30:12+00:00

Show all

2017

Filntisis, Panagiotis Paraskevas; Katsamanis, Athanasios; Tsiakoulis, Pirros; Maragos, Petros

Video-realistic expressive audio-visual speech synthesis for the Greek language Journal Article

Speech Communication, 95 , pp. 137–152, 2017, ISSN: 01676393.

Abstract | BibTeX | Tags: adaptation, Audio-visual speech synthesis, Deep neural networks, Expressive, hidden Markov models, Interpolation | Links: pdf link imagedoi link image

2008

Caridakis, George; Diamanti, Olga; Karpouzis, Kostas; Maragos, Petros

Automatic sign language recognition Conference

Proceedings of the 1st ACM international conference on PErvasive Technologies Related to Assistive Environments - PETRA '08, 2008, ISBN: 9781605580678.

Abstract | BibTeX | Tags: geodesic active contour models, gesture recognition, hidden Markov models, image seg-, maps, markov models, mentation, optical flow, self-organizing, sign language recognition | Links: pdf link imagedoi link image

2002

Dimitriadis, D; Maragos, P; Potamianos, A

Modulation features for speech recognition Conference

International Conference on Acoustics, 1 , 2002.

BibTeX | Tags: acoustic features, acoustic processing, ASR systems, automatic speech recognition, cepstral analysis, feature extraction, hidden Markov models, HMM-based word recognition, mel-frequency cepstrum, modulation, modulation type, nonlinear phenomena, nonlinear systems, robust methods, speech analysis, speech production, speech recognition, speech signals, time-varying models, time-varying phenomena, time-varying systems, TIMIT database

Pitsikalis, V; Maragos, P

Speech analysis and feature extraction using chaotic models Conference

International Conference on Acoustics, 1 , 2002.

BibTeX | Tags: acoustic signal processing, cepstral analysis, cepstrum, chaos, chaos theory, chaotic models, feature extraction, generalized hybrid set, hidden Markov models, HMM, multidimensional phase space, multidimensional signal processing, nonlinear acoustic features, nonlinear dynamic systems, nonlinear dynamical systems, short-time acoustic features, speech analysis, speech processing, speech production, speech recognition, speech signal modeling, speech signals, speech synthesis, word recognition

Dimitriadis, D; Maragos, P; Potamianos, A

Modulation features for speech recognition Journal Article

International Conference on Acoustics, 1 , pp. I–377–I–380, 2002.

BibTeX | Tags: acoustic features, acoustic processing, ASR systems, automatic speech recognition, cepstral analysis, feature extraction, hidden Markov models, HMM-based word recognition, mel-frequency cepstrum, modulation, modulation type, nonlinear phenomena, nonlinear systems, robust methods, speech analysis, speech production, speech recognition, speech signals, time-varying models, time-varying phenomena, time-varying systems, TIMIT database | Links: pdf link image