Themos Stafylakis

According to our database, Themos Stafylakis authored at least 76 papers between 2007 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

Do End-to-End Neural Diarization Attractors Need to Encode Speaker Characteristic Information?

Lin Zhang, Themos Stafylakis, Federico Landini, Mireia Díez, Anna Silnova, Lukás Burget

CoRR, 2024

2023

KAN-AV dataset for audio-visual face and speech analysis in the wild.

Triantafyllos Kefalas, Eftychia Fotiadou, Markos Georgopoulos, Yannis Panagakis, Pingchuan Ma, Stavros Petridis, Themos Stafylakis, Maja Pantic

Image Vis. Comput., December, 2023

DiaPer: End-to-End Neural Diarization with Perceiver-Based Attractors.

Federico Landini, Mireia Díez, Themos Stafylakis, Lukás Burget

CoRR, 2023

Parameter-Efficient Transfer Learning of Pre-Trained Transformer Models for Speaker Verification Using Adapters.

Junyi Peng, Themos Stafylakis, Rongzhi Gu, Oldrich Plchot, Ladislav Mosner, Lukás Burget, Jan Cernocký

Proceedings of the IEEE International Conference on Acoustics, 2023

Speech-Based Emotion Recognition with Self-Supervised Models Using Attentive Channel-Wise Correlations and Label Smoothing.

Sofoklis Kakouros, Themos Stafylakis, Ladislav Mosner, Lukás Burget

Proceedings of the IEEE International Conference on Acoustics, 2023

A Simple Baseline for Knowledge-Based Visual Question Answering.

Alexandros Xenos, Themos Stafylakis, Ioannis Patras, Georgios Tzimiropoulos

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023

2022

Extracting Speaker and Emotion Information from Self-Supervised Speech Models via Channel-Wise Correlations.

Themos Stafylakis, Ladislav Mosner, Sofoklis Kakouros, Oldrich Plchot, Lukás Burget, Jan Cernocký

Proceedings of the IEEE Spoken Language Technology Workshop, 2022

An Attention-Based Backend Allowing Efficient Fine-Tuning of Transformer Models for Speaker Verification.

Junyi Peng, Oldrich Plchot, Themos Stafylakis, Ladislav Mosner, Lukás Burget, Jan Cernocký

Proceedings of the IEEE Spoken Language Technology Workshop, 2022

On the Use of Semantically-Aligned Speech Representations for Spoken Language Understanding.

Gaëlle Laperrière, Valentin Pelloin, Mickaël Rouvier, Themos Stafylakis, Yannick Estève

Proceedings of the IEEE Spoken Language Technology Workshop, 2022

Analyzing Speaker Verification Embedding Extractors and Back-Ends Under Language and Channel Mismatch.

Anna Silnova, Themos Stafylakis, Ladislav Mosner, Oldrich Plchot, Johan Rohdin, Pavel Matejka, Lukás Burget, Ondrej Glembek, Niko Brummer

Proceedings of the Odyssey 2022: The Speaker and Language Recognition Workshop, 28 June, 2022

Development of ABC Systems for the 2021 Edition of NIST Speaker Recognition Evaluation.

Jahangir Alam, Radek Benes, Marian Beszédes, Lukás Burget, Mohamed Dahmane, Abderrahim Fathan, Hamed Ghodrati, Ondrej Glembek, Woo Hyun Kang, Pavel Matejka, Ladislav Mosner, Oldrich Plchot, Johan Rohdin, Anna Silnova, Themos Stafylakis

Proceedings of the Odyssey 2022: The Speaker and Language Recognition Workshop, 28 June, 2022

Training speaker embedding extractors using multi-speaker audio with unknown speaker boundaries.

Themos Stafylakis, Ladislav Mosner, Oldrich Plchot, Johan Rohdin, Anna Silnova, Lukás Burget, Jan Cernocký

Proceedings of the Interspeech 2022, 2022

Probabilistic Spherical Discriminant Analysis: An Alternative to PLDA for length-normalized embeddings.

Niko Brummer, Albert Swart, Ladislav Mosner, Anna Silnova, Oldrich Plchot, Themos Stafylakis, Lukás Burget

Proceedings of the Interspeech 2022, 2022

2021

Speaker Embeddings by Modeling Channel-Wise Correlations.

Themos Stafylakis, Johan Rohdin, Lukás Burget

Proceedings of the Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August, 2021

2020

Probabilistic Embeddings for Speaker Diarization.

Anna Silnova, Niko Brummer, Johan Rohdin, Themos Stafylakis, Lukás Burget

Proceedings of the Odyssey 2020: The Speaker and Language Recognition Workshop, 2020

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

Jahangir Alam, Gilles Boulianne, Lukás Burget, Mohamed Dahmane, Mireia Díez Sánchez, Alicia Lozano-Diez, Ondrej Glembek, Pierre-Luc St-Charles, Marc Lalonde, Pavel Matejka, Petr Mizera, João Monteiro, Ladislav Mosner, Cedric Noiseux, Ondrej Novotný, Oldrich Plchot, Johan Rohdin, Anna Silnova, Josef Slavícek, Themos Stafylakis, Shuai Wang, Hossein Zeinali

Proceedings of the Odyssey 2020: The Speaker and Language Recognition Workshop, 2020

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

Elisavet Palogiannidi, Ioannis Gkinis, George Mastrapas, Petr Mizera, Themos Stafylakis

Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

Seeing wake words: Audio-visual Keyword Spotting.

Liliane Momeni, Triantafyllos Afouras, Themos Stafylakis, Samuel Albanie, Andrew Zisserman

Proceedings of the 31st British Machine Vision Conference 2020, 2020

2019

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

Nooshin Maghsoodi, Hossein Sameti, Hossein Zeinali, Themos Stafylakis

IEEE ACM Trans. Audio Speech Lang. Process., 2019

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

Hossein Zeinali, Themos Stafylakis, Georgia Athanasopoulou, Johan Rohdin, Ioannis Gkinis, Lukás Burget, Jan Cernocký

Proceedings of the Interspeech 2019, 2019

Self-Supervised Speaker Embeddings.

Themos Stafylakis, Johan Rohdin, Oldrich Plchot, Petr Mizera, Lukás Burget

Proceedings of the Interspeech 2019, 2019

Privacy-Preserving Speaker Recognition with Cohort Score Normalisation.

Andreas Nautsch, Jose Patino, Amos Treiber, Themos Stafylakis, Petr Mizera, Massimiliano Todisco, Thomas Schneider, Nicholas W. D. Evans

Proceedings of the Interspeech 2019, 2019

How to Improve Your Speaker Embeddings Extractor in Generic Toolkits.

Hossein Zeinali, Lukás Burget, Johan Rohdin, Themos Stafylakis, Jan Honza Cernocký

Proceedings of the IEEE International Conference on Acoustics, 2019

Speaker Verification Using End-to-end Adversarial Language Adaptation.

Johan Rohdin, Themos Stafylakis, Anna Silnova, Hossein Zeinali, Lukás Burget, Oldrich Plchot

Proceedings of the IEEE International Conference on Acoustics, 2019

2018

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

Themos Stafylakis, Muhammad Haris Khan, Georgios Tzimiropoulos

Comput. Vis. Image Underst., 2018

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

Stavros Petridis, Themos Stafylakis, Pingchuan Ma, Georgios Tzimiropoulos, Maja Pantic

Proceedings of the 2018 IEEE Spoken Language Technology Workshop, 2018

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

Hossein Zeinali, Hossein Sameti, Themos Stafylakis

Proceedings of the Odyssey 2018: The Speaker and Language Recognition Workshop, 2018

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

Niko Brummer, Anna Silnova, Lukás Burget, Themos Stafylakis

Proceedings of the Odyssey 2018: The Speaker and Language Recognition Workshop, 2018

Deep Word Embeddings for Visual Speech Recognition.

Themos Stafylakis, Georgios Tzimiropoulos

Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

End-to-End Audiovisual Speech Recognition.

Stavros Petridis, Themos Stafylakis, Pingchuan Ma, Feipeng Cai, Georgios Tzimiropoulos, Maja Pantic

Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

Zero-Shot Keyword Spotting for Visual Speech Recognition In-the-wild.

Themos Stafylakis, Georgios Tzimiropoulos

Proceedings of the Computer Vision - ECCV 2018, 2018

2017

Combining Residual Networks with LSTMs for Lipreading.

Themos Stafylakis, Georgios Tzimiropoulos

Proceedings of the Interspeech 2017, 2017

The I4U Mega Fusion and Collaboration for NIST Speaker Recognition Evaluation 2016.

Kong-Aik Lee, Ville Hautamäki, Tomi Kinnunen, Anthony Larcher, Chunlei Zhang, Andreas Nautsch, Themos Stafylakis, Gang Liu, Mickaël Rouvier, Wei Rao, Federico Alegre, J. Ma, Man-Wai Mak, Achintya Kumar Sarkar, Héctor Delgado, Rahim Saeidi, Hagai Aronowitz, Aleksandr Sizov, Hanwu Sun, Trung Hieu Nguyen, G. Wang, Bin Ma, Ville Vestman, Md. Sahidullah, M. Halonen, Anssi Kanervisto, Gaël Le Lan, Fahimeh Bahmaninezhad, Sergey Isadskiy, Christian Rathgeb, Christoph Busch, Georgios Tzimiropoulos, Q. Qian, Z. Wang, Q. Zhao, T. Wang, H. Li, J. Xue, S. Zhu, R. Jin, T. Zhao, Pierre-Michel Bousquet, Moez Ajili, Waad Ben Kheder, Driss Matrouf, Zhi Hao Lim, Chenglin Xu, Haihua Xu, Xiong Xiao, Eng Siong Chng, Benoit G. B. Fauve, Kaavya Sriskandaraja, Vidhyasaharan Sethu, W. W. Lin, Dennis Alexander Lehmann Thomsen, Zheng-Hua Tan, Massimiliano Todisco, Nicholas W. D. Evans, Haizhou Li, John H. L. Hansen, Jean-François Bonastre, Eliathamby Ambikairajah

Proceedings of the Interspeech 2017, 2017

2016

Speaker and Channel Factors in Text-Dependent Speaker Recognition.

Themos Stafylakis, Patrick Kenny, Md. Jahangir Alam, Marcel Kockmann

IEEE ACM Trans. Audio Speech Lang. Process., 2016

Text-Dependent Speaker Recognition With Random Digit Strings.

Themos Stafylakis, Md. Jahangir Alam, Patrick Kenny

IEEE ACM Trans. Audio Speech Lang. Process., 2016

Compensation for phonetic nuisance variability in speaker recognition using DNNs.

Themos Stafylakis, Patrick Kenny, Vishwa Gupta, Md. Jahangir Alam, Marcel Kockmann

Proceedings of the Odyssey 2016: The Speaker and Language Recognition Workshop, 2016

Uncertainty Modeling Without Subspace Methods For Text-Dependent Speaker Recognition.

Patrick Kenny, Themos Stafylakis, Md. Jahangir Alam, Vishwa Gupta, Marcel Kockmann

Proceedings of the Odyssey 2016: The Speaker and Language Recognition Workshop, 2016

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

Gautam Bhattacharya, Patrick Kenny, Md. Jahangir Alam, Themos Stafylakis

Proceedings of the Odyssey 2016: The Speaker and Language Recognition Workshop, 2016

Spoofing Detection on the ASVspoof2015 Challenge Corpus Employing Deep Neural Networks.

Md. Jahangir Alam, Patrick Kenny, Vishwa Gupta, Themos Stafylakis

Proceedings of the Odyssey 2016: The Speaker and Language Recognition Workshop, 2016

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

Andreas Nautsch, Hong Hao, Themos Stafylakis, Christian Rathgeb, Christoph Busch

Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

2015

JFA for speaker recognition with random digit strings.

Themos Stafylakis, Patrick Kenny, Md. Jahangir Alam, Marcel Kockmann

Proceedings of the INTERSPEECH 2015, 2015

The reddots data collection for speaker recognition.

Kong-Aik Lee, Anthony Larcher, Guangsen Wang, Patrick Kenny, Niko Brümmer, David A. van Leeuwen, Hagai Aronowitz, Marcel Kockmann, Carlos Vaquero, Bin Ma, Haizhou Li, Themos Stafylakis, Md. Jahangir Alam, Albert Swart, Javier Perez

Proceedings of the INTERSPEECH 2015, 2015

An i-vector backend for speaker verification.

Patrick Kenny, Themos Stafylakis, Md. Jahangir Alam, Marcel Kockmann

Proceedings of the INTERSPEECH 2015, 2015

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

Md. Jahangir Alam, Patrick Kenny, Themos Stafylakis

Proceedings of the INTERSPEECH 2015, 2015

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

Md. Jahangir Alam, Patrick Kenny, Gautam Bhattacharya, Themos Stafylakis

Proceedings of the INTERSPEECH 2015, 2015

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

Patrick Kenny, Themos Stafylakis, Md. Jahangir Alam, Marcel Kockmann

Proceedings of the 2015 IEEE International Conference on Acoustics, 2015

2014

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

Mohammed Senoussaoui, Patrick Kenny, Themos Stafylakis, Pierre Dumouchel

IEEE ACM Trans. Audio Speech Lang. Process., 2014

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

Patrick Kenny, Themos Stafylakis, Pierre Ouellet, Vishwa Gupta, Md. Jahangir Alam

Proceedings of the Odyssey 2014: The Speaker and Language Recognition Workshop, 2014

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

Patrick Kenny, Themos Stafylakis, Pierre Ouellet, Md. Jahangir Alam, Pierre Dumouchel

Proceedings of the Odyssey 2014: The Speaker and Language Recognition Workshop, 2014

Joint Factor Analysis for Text-Dependent Speaker Verification.

Patrick Kenny, Themos Stafylakis, Md. Jahangir Alam, Pierre Ouellet, Marcel Kockmann

Proceedings of the Odyssey 2014: The Speaker and Language Recognition Workshop, 2014

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

Patrick Kenny, Themos Stafylakis, Md. Jahangir Alam, Pierre Ouellet, Marcel Kockmann

Proceedings of the INTERSPEECH 2014, 2014

JFA-based front ends for speaker recognition.

Patrick Kenny, Themos Stafylakis, Pierre Ouellet, Md. Jahangir Alam

Proceedings of the IEEE International Conference on Acoustics, 2014

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

Vishwa Gupta, Patrick Kenny, Pierre Ouellet, Themos Stafylakis

Proceedings of the IEEE International Conference on Acoustics, 2014

Unscented transform for ivector-based noisy speaker recognition.

David Martínez González, Lukás Burget, Themos Stafylakis, Yun Lei, Patrick Kenny, Eduardo Lleida

Proceedings of the IEEE International Conference on Acoustics, 2014

2013

Text-dependent speaker recognition using PLDA with uncertainty propagation.

Themos Stafylakis, Patrick Kenny, Pierre Ouellet, Javier Perez, Marcel Kockmann, Pierre Dumouchel

Proceedings of the INTERSPEECH 2013, 2013

Compensation for inter-frame correlations in speaker diarization and recognition.

Themos Stafylakis, Patrick Kenny, Vishwa Gupta, Pierre Dumouchel

Proceedings of the IEEE International Conference on Acoustics, 2013

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

Mohammed Senoussaoui, Patrick Kenny, Pierre Dumouchel, Themos Stafylakis

Proceedings of the IEEE International Conference on Acoustics, 2013

PLDA for speaker verification with utterances of arbitrary duration.

Patrick Kenny, Themos Stafylakis, Pierre Ouellet, Md. Jahangir Alam, Pierre Dumouchel

Proceedings of the IEEE International Conference on Acoustics, 2013

2012

Preliminary investigation of Boltzmann machine classifiers for speaker recognition.

Themos Stafylakis, Patrick Kenny, Mohammed Senoussaoui, Pierre Dumouchel

Proceedings of the Odyssey 2012: The Speaker and Language Recognition Workshop, 2012

Mean shift algorithm for exponential families with applications to speaker clustering.

Themos Stafylakis, Vassilis Katsouros, Patrick Kenny, Pierre Dumouchel

Proceedings of the Odyssey 2012: The Speaker and Language Recognition Workshop, 2012

A mean shift algorithm for manifolds of exponential families.

Themos Stafylakis, Vassilis Katsouros, Patrick Kenny, Pierre Dumouchel

Proceedings of the 11th International Conference on Information Science, 2012

PLDA using Gaussian Restricted Boltzmann Machines with application to Speaker Verification.

Themos Stafylakis, Patrick Kenny, Mohammed Senoussaoui, Pierre Dumouchel

Proceedings of the INTERSPEECH 2012, 2012

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

Aggelos Gkiokas, Vassilis Katsouros, George Carayannis, Themos Stafylakis

Proceedings of the 2012 IEEE International Conference on Acoustics, 2012

2011

Developing a Scoring Algorithm for Automatic Pronunciation Assessment of Modern Greek.

Frieda Charalabopoulou, Themos Stafylakis, George K. Mikros

J. Quant. Linguistics, 2011

Enhancing Handwritten Word Segmentation by Employing Local Spatial Features.

Fotini Simistira, Vassilis Papavassiliou, Themos Stafylakis, Vassilis Katsouros

Proceedings of the 2011 International Conference on Document Analysis and Recognition, 2011

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

Themos Stafylakis, Xavier Anguera Miró, Vassilis Katsouros, George Carayannis

Proceedings of the IEEE International Conference on Acoustics, 2011

2010

Handwritten document image segmentation into text lines and words.

Vassilis Papavassiliou, Themos Stafylakis, Vassilis Katsouros, George Carayannis

Pattern Recognit., 2010

The Segmental Bayesian Information Criterion and Its Applications to Speaker Diarization.

Themos Stafylakis, Vassilis Katsouros, George Carayannis

IEEE J. Sel. Top. Signal Process., 2010

Speaker clustering via the mean shift algorithm.

Themos Stafylakis, Vassilis Katsouros, George Carayannis

Proceedings of the Odyssey 2010: The Speaker and Language Recognition Workshop, Brno, Czech Republic, June 28, 2010

Improvements to the equal-parameter BIC for speaker diarization.

Themos Stafylakis, Xavier Anguera

Proceedings of the INTERSPEECH 2010, 2010

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

Themos Stafylakis, Georgios Tzimiropoulos, Vassilis Katsouros, George Carayannis

Proceedings of the IEEE International Conference on Acoustics, 2010

2009

Redefining the Bayesian information criterion for speaker diarisation.

Themos Stafylakis, Vassilis Katsouros, George Carayannis

Proceedings of the INTERSPEECH 2009, 2009

2008

Robust text-line and word segmentation for handwritten documents images.

Themos Stafylakis, Vassilis Papavassiliou, Vassilis Katsouros, George Carayannis

Proceedings of the IEEE International Conference on Acoustics, 2008

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

Iason Demiros, George Carayannis, Vassilios Antonopoulos, Georgios Kambourakis, Vassilios Katsouros, Panayotis Kolevris, Marios Nottas, Harris Papageorgiou, Vassilis Papavassiliou, Spyros Raptis, Fotini Simistira, Themos Stafylakis

Proceedings of the 19th International Workshop on Database and Expert Systems Applications (DEXA 2008), 2008

2007

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

Vassilis Papavassiliou, Themos Stafylakis, Vassilis Katsouros, George Carayannis

Proceedings of the 9th International Conference on Document Analysis and Recognition (ICDAR 2007), 2007

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

Themos Stafylakis, Vassilis Katsouros, George Carayannis

Proceedings of the IEEE Workshop on Automatic Speech Recognition & Understanding, 2007