Year: <span>2022</span>

Speech-based emotion recognition with self-supervised models using attentive channel-wise correlations and label smoothing Authors: Sofoklis Kakouros, Themos Stafylakis, Ladislav Mosner, Lukas Burget Collaborators: University of Helsinki, FinlandOmilia – Conversational Intelligence, Athens, GreeceBrno University of Technology,...

Parameter-efficient transfer learning of pre-trained Transformer models for speaker verification using adapters Authors: Junyi Peng, Themos Stafylakis, Rongzhi Gu, Oldřich Plchot, Ladislav Mošner, Lukáš Burget, Jan ČernockýColaborators: Brno University of Technology, Faculty of Information Technology,...

Extracting speaker and emotion information from self-supervised speech models via channel-wise correlations Authors: Themos Stafylakis, Ladislav Mosner, Sofoklis Kakouros, Oldrich Plchot, Lukas Burget, Jan CernockyColaborators: Brno University of Technology, Faculty of Information Technology, Speech@FIT, CzechiaOmilia...

On the Use of Semantically-Aligned Speech Representations for Spoken Language Understanding Authors: G Laperrière, V Pelloin, M Rouvier, T Stafylakis, Y EstèveColaborators: LIA – Avignon Universite, FranceLIUM – Le Mans Universite, FranceOmilia – Conversational Intelligence,...

An attention-based backend allowing efficient fine-tuning of transformer models for speaker verification Authors: Junyi Peng, Oldrich Plchot, Themos Stafylakis, Ladislav Mosner, Lukas Burget, Jan CernockyColaborators: Brno University of Technology, Faculty of Information Technology, Speech@FIT, CzechiaOmilia...

Seeing wake words: Audio-visual Keyword Spotting Authors: Liliane Momeni, Triantafyllos Afouras, Themos Stafylakis, Samuel Albanie, Andrew ZissermanColaborators: Visual Geometry Group Department of Engineering Science University of Oxford Oxford, UKOmilia Conversational Intelligence Athens, Greece Publication Date...

Training Speaker Embedding Extractors Using Multi-Speaker Audio with Unknown Speaker Boundaries Authors: Themos Stafylakis, Ladislav Mošner, Oldřich Plchot, Johan Rohdin, Anna Silnova, Lukáš Burget, Jan ČernockýColaborators: Brno University of Technology, Faculty of Information Technology, Speech@FIT,...

Probabilistic Spherical Discriminant Analysis: An Alternative to PLDA for length-normalized embeddings Authors: Niko Brümmer, Albert Swart, Ladislav Mošner, Anna Silnova, Oldřich Plchot, Themos Stafylakis, Lukáš BurgetColaborators: Brno University of Technology, Faculty of Information Technology, Speech@FIT,...

Development of ABC Systems for the 2021 Edition of NIST Speaker Recognition Evaluation Authors: Jahangir Alam, Radek Beneš, Marián Beszédeš, Lukáš Burget, Mohamed Dahmane, Abderrahim Fathan, Hamed Ghodrati, Ondřej Glembek, Woo Hyun Kang, Pavel Matĕjka,...

Analyzing speaker verification embedding extractors and back-ends under language and channel mismatch Authors: Anna Silnova, Themos Stafylakis, Ladislav Mosner, Oldrich Plchot, Johan Rohdin, Pavel Matejka, Lukas Burget, Ondrej Glembek, Niko BrummerColaborators: Brno University of Technology,...