Themos Stafylakis

发表

A mean shift algorithm for manifolds of exponential families

Vassilis Katsouros, Themos Stafylakis, Patrick Kenny, 2012, 2012 11th International Conference on Information Science, Signal Processing and their Applications (ISSPA).

Developing a Scoring Algorithm for Automatic Pronunciation Assessment of Modern Greek

Themos Stafylakis, Frieda Charalabopoulou, George K. Mikros, 2011, J. Quant. Linguistics.

Self-supervised speaker embeddings

Lukás Burget, Themos Stafylakis, Johan Rohdin, 2019, INTERSPEECH.

Privacy-Preserving Speaker Recognition with Cohort Score Normalisation

Nicholas Evans, Themos Stafylakis, Thomas Schneider, 2019, INTERSPEECH.

Compensation for inter-frame correlations in speaker diarization and recognition

Themos Stafylakis, Patrick Kenny, Pierre Dumouchel, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Unscented transform for ivector-based noisy speaker recognition

Yun Lei, Lukás Burget, Themos Stafylakis, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Deep Neural Networks for extracting Baum-Welch statistics for Speaker Recognition

Themos Stafylakis, Patrick Kenny, Pierre Ouellet, 2014, Odyssey.

Towards PLDA-RBM based speaker recognition in mobile environment: Designing stacked/deep PLDA-RBM systems

Christoph Busch, Hong Hao, Themos Stafylakis, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Robust text-line and word segmentation for handwritten documents images

Vassilis Katsouros, George Carayannis, Themos Stafylakis, 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

Text-Dependent Speaker Recognition With Random Digit Strings

Themos Stafylakis, Patrick Kenny, Md. Jahangir Alam, 2016, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Speaker Recognition With Random Digit Strings Using Uncertainty Normalized HMM-Based i-Vectors

Hossein Sameti, Themos Stafylakis, Nooshin Maghsoodi, 2019, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

A Study of the Cosine Distance-Based Mean Shift for Telephone Speech Diarization

Themos Stafylakis, Patrick Kenny, Mohammed Senoussaoui, 2014, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Text-dependent speaker recognition using PLDA with uncertainty propagation

Themos Stafylakis, Patrick Kenny, Pierre Dumouchel, 2013, INTERSPEECH.

The reddots data collection for speaker recognition

Bin Ma, Haizhou Li, Hagai Aronowitz, 2015, INTERSPEECH.

Preliminary investigation of Boltzmann machine classifiers for speaker recognition

Themos Stafylakis, Patrick Kenny, Pierre Dumouchel, 2012, Odyssey.

Development of CRIM system for the automatic speaker verification spoofing and countermeasures challenge 2015

Themos Stafylakis, Patrick Kenny, Gautam Bhattacharya, 2015, INTERSPEECH.

Joint Factor Analysis for Text-Dependent Speaker Verification

Themos Stafylakis, Patrick Kenny, Pierre Ouellet, 2014, Odyssey.

Seeing wake words: Audio-visual Keyword Spotting pdf

Andrew Zisserman, Themos Stafylakis, Triantafyllos Afouras, 2020, BMVC.

Zero-shot keyword spotting for visual speech recognition in-the-wild

Themos Stafylakis, Georgios Tzimiropoulos, Georgios Tzimiropoulos, 2018, ECCV.

Spoofing Detection on the ASVspoof2015 Challenge Corpus Employing Deep Neural Networks

Themos Stafylakis, Patrick Kenny, Vishwa Gupta, 2016, Odyssey.

Supervised/Unsupervised Voice Activity Detectors for Text-dependent Speaker Recognition on the RSR2015 Corpus

Themos Stafylakis, Patrick Kenny, Pierre Dumouchel, 2014, Odyssey.

Enhancing Handwritten Word Segmentation by Employing Local Spatial Features

Fotini Simistira, Vassilis Katsouros, Themos Stafylakis, 2011, 2011 International Conference on Document Analysis and Recognition.

Probabilistic embeddings for speaker diarization pdf

Themos Stafylakis, Luk'avs Burget, Johan Rohdin, 2020, Odyssey.

The Segmental Bayesian Information Criterion and Its Applications to Speaker Diarization

Vassilis Katsouros, George Carayannis, Themos Stafylakis, 2010, IEEE Journal of Selected Topics in Signal Processing.

Detecting Spoofing Attacks Using VGG and SincNet: BUT-Omilia Submission to ASVspoof 2019 Challenge

Lukás Burget, Themos Stafylakis, Hossein Zeinali, 2019, INTERSPEECH.

Uncertainty Modeling Without Subspace Methods For Text-Dependent Speaker Recognition

Themos Stafylakis, Patrick Kenny, Vishwa Gupta, 2016, Odyssey.

How to Improve Your Speaker Embeddings Extractor in Generic Toolkits

Themos Stafylakis, Johan Rohdin, Hossein Zeinali, 2018, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

DeepMine Speech Processing Database: Text-Dependent and Independent Speaker Verification and Speech Recognition in Persian and English

Hossein Sameti, Themos Stafylakis, Hossein Zeinali, 2018, Odyssey.

Closed-form expressions vs. BIC: A comparison for speaker clustering

Vassilis Katsouros, George Carayannis, Themos Stafylakis, 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

A Review of Recent Advances in Speaker Diarization with Bayesian Methods

Themos Stafylakis, Vassilis Katsouros, Themos Stafylakis, 2011 .

Music tempo estimation and beat tracking by applying source separation and metrical relations

Vassilis Katsouros, George Carayannis, Themos Stafylakis, 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

A Parametric Spectral-Based Method for Verification of Text in Videos

Vassilis Katsouros, George Carayannis, Themos Stafylakis, 2007, Ninth International Conference on Document Analysis and Recognition (ICDAR 2007).

End-to-End Architectures for ASR-Free Spoken Language Understanding

Themos Stafylakis, Petr Mizera, Ioannis Gkinis, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

JFA for speaker recognition with random digit strings

Themos Stafylakis, Patrick Kenny, Md. Jahangir Alam, 2015, INTERSPEECH.

Handwritten document image segmentation into text lines and words

Vassilis Katsouros, George Carayannis, Themos Stafylakis, 2010, Pattern Recognit..

A Parametric Spectral-Based Method for Verification of Text in Videos

Vassilis Katsouros, Themos Stafylakis, Vassilis Papavassiliou, 2007 .

PLDA using Gaussian Restricted Boltzmann Machines with application to Speaker Verification

Themos Stafylakis, Patrick Kenny, Pierre Dumouchel, 2012, INTERSPEECH.

Audio-Visual Speech Recognition with a Hybrid CTC/Attention Architecture

Maja Pantic, Themos Stafylakis, Georgios Tzimiropoulos, 2018, 2018 IEEE Spoken Language Technology Workshop (SLT).

Speaker clustering via the mean shift algorithm

Vassilis Katsouros, George Carayannis, Themos Stafylakis, 2010, Odyssey.

An i-vector backend for speaker verification

Themos Stafylakis, Patrick Kenny, Md. Jahangir Alam, 2015, INTERSPEECH.

Redefining the Bayesian information criterion for speaker diarisation

Vassilis Katsouros, George Carayannis, Themos Stafylakis, 2009, INTERSPEECH.

Compensation for phonetic nuisance variability in speaker recognition using DNNs

Themos Stafylakis, Patrick Kenny, Vishwa Gupta, 2016, Odyssey.

Deep Neural Network based Text-Dependent Speaker Verification : Preliminary Results

Themos Stafylakis, Patrick Kenny, Gautam Bhattacharya, 2016, Odyssey.

Combining amplitude and phase-based features for speaker verification with short duration utterances

Themos Stafylakis, Patrick Kenny, Md. Jahangir Alam, 2015, INTERSPEECH.

End-to-End Audiovisual Speech Recognition

Maja Pantic, Themos Stafylakis, Georgios Tzimiropoulos, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Mean shift algorithm for exponential families with applications to speaker clustering

Vassilis Katsouros, Themos Stafylakis, Patrick Kenny, 2012, Odyssey.

In-domain versus out-of-domain training for text-dependent JFA

Themos Stafylakis, Patrick Kenny, Pierre Ouellet, 2014, INTERSPEECH.

Pushing the boundaries of audiovisual word recognition using Residual Networks and LSTMs pdf

Themos Stafylakis, Georgios Tzimiropoulos, Muhammad Haris Khan, 2018, Comput. Vis. Image Underst..

Combining Residual Networks with LSTMs for Lipreading pdf

Themos Stafylakis, Georgios Tzimiropoulos, Georgios Tzimiropoulos, 2017, INTERSPEECH.

Deep Word Embeddings for Visual Speech Recognition

Themos Stafylakis, Georgios Tzimiropoulos, Georgios Tzimiropoulos, 2017, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Efficient combination of parametric spaces, models and metrics for speaker diarization1

Vassilis Katsouros, George Carayannis, Themos Stafylakis, 2007, 2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU).

PLDA for speaker verification with utterances of arbitrary duration

Themos Stafylakis, Patrick Kenny, Pierre Dumouchel, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Gaussian meta-embeddings for efficient scoring of a heavy-tailed PLDA model

Lukás Burget, Themos Stafylakis, Niko Brümmer, 2018, Odyssey.

Speaker Verification Using End-to-end Adversarial Language Adaptation

Lukás Burget, Themos Stafylakis, Hossein Zeinali, 2018, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

JFA-based front ends for speaker recognition

Themos Stafylakis, Patrick Kenny, Pierre Ouellet, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

I-vector-based speaker adaptation of deep neural networks for French broadcast audio transcription

Themos Stafylakis, Patrick Kenny, Pierre Ouellet, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

JFA modeling with left-to-right structure and a new backend for text-dependent speaker recognition

Themos Stafylakis, Patrick Kenny, Md. Jahangir Alam, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

PANOPTIS: A System for Intelligent Monitoring of the Hellenic Broadcast Sector

Georgios Kambourakis, Fotini Simistira, George Carayannis, 2008, 2008 19th International Workshop on Database and Expert Systems Applications.

Improvements to the equal-parameter BIC for speaker diarization

Themos Stafylakis, Xavier Anguera Miró, 2010, INTERSPEECH.

Efficient iterative mean shift based cosine dissimilarity for multi-recording speaker clustering

Themos Stafylakis, Patrick Kenny, Pierre Dumouchel, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Analysis of ABC Submission to NIST SRE 2019 CMN and VAST Challenge

Themos Stafylakis, Pierre-Luc St-Charles, Gilles Boulianne, 2020 .

A new penalty term for the BIC with respect to speaker diarization

Vassilis Katsouros, George Carayannis, Themos Stafylakis, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

Speaker and Channel Factors in Text-Dependent Speaker Recognition

Themos Stafylakis, Patrick Kenny, Md. Jahangir Alam, 2016, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Speaker embeddings by modeling channel-wise correlations pdf

Themos Stafylakis, Lukas Burget, Johan Rohdin, 2021, Interspeech.

End-to-End Audiovisual Speech Recognition

Maja Pantic, Themos Stafylakis, Georgios Tzimiropoulos, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).