Themos Stafylakis | DeepAI

DeepAI AI Chat

Featured Co-authors

Andrew Zisserman
174 publications
Maja Pantic
76 publications
Georgios Tzimiropoulos
60 publications
Lukas Burget
45 publications
Samuel Albanie
43 publications
Nicholas Evans
41 publications
Stavros Petridis
40 publications
Pingchuan Ma
36 publications
Massimiliano Todisco
33 publications
Yannick Estève
26 publications
Jose Patino
23 publications

∙ 11/03/2022

Speech-based emotion recognition with self-supervised models using attentive channel-wise correlations and label smoothing

When recognizing emotions from speech, we encounter two common problems:...

0 Sofoklis Kakouros, et al. ∙

∙ 10/28/2022

Parameter-efficient transfer learning of pre-trained Transformer models for speaker verification using adapters

Recently, the pre-trained Transformer models have received a rising inte...

0 Junyi Peng, et al. ∙

∙ 10/15/2022

Extracting speaker and emotion information from self-supervised speech models via channel-wise correlations

Self-supervised learning of speech representations from large amounts of...

0 Themos Stafylakis, et al. ∙

∙ 10/11/2022

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

In this paper we examine the use of semantically-aligned speech represen...

0 Gaëlle Laperrière, et al. ∙

∙ 03/28/2022

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

In speaker recognition, where speech segments are mapped to embeddings o...

0 Niko Brümmer, et al. ∙

∙ 04/06/2021

Speaker embeddings by modeling channel-wise correlations

Speaker embeddings extracted with deep 2D convolutional neural networks ...

0 Themos Stafylakis, et al. ∙

∙ 09/02/2020

Seeing wake words: Audio-visual Keyword Spotting

The goal of this work is to automatically determine whether and when a w...

6 Liliane Momeni, et al. ∙

∙ 04/06/2020

Probabilistic embeddings for speaker diarization

Speaker embeddings (x-vectors) extracted from very short segments of spe...

5 Anna Silnova, et al. ∙

∙ 07/13/2019

Speaker Recognition with Random Digit Strings Using Uncertainty Normalized HMM-based i-vectors

In this paper, we combine Hidden Markov Models (HMMs) with i-vector extr...

0 Nooshin Maghsoodi, et al. ∙

∙ 07/13/2019

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

In this paper, we present the system description of the joint efforts of...

0 Hossein Zeinali, et al. ∙

∙ 07/08/2019

Privacy-Preserving Speaker Recognition with Cohort Score Normalisation

In many voice biometrics applications there is a requirement to preserve...

0 Andreas Nautsch, et al. ∙

∙ 04/06/2019

Self-supervised speaker embeddings

Contrary to i-vectors, speaker embeddings such as x-vectors are incapabl...

2 Themos Stafylakis, et al. ∙

∙ 11/06/2018

Speaker verification using end-to-end adversarial language adaptation

In this paper we investigate the use of adversarial domain adaptation fo...

0 Johan Rohdin, et al. ∙

∙ 11/05/2018

How to Improve Your Speaker Embeddings Extractor in Generic Toolkits

Recently, speaker embeddings extracted with deep neural networks became ...

0 Hossein Zeinali, et al. ∙

∙ 11/03/2018

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

Visual and audiovisual speech recognition are witnessing a renaissance w...

0 Themos Stafylakis, et al. ∙

∙ 09/28/2018

Audio-Visual Speech Recognition With A Hybrid CTC/Attention Architecture

Recent works in speech recognition rely either on connectionist temporal...

0 Stavros Petridis, et al. ∙

∙ 07/23/2018

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

Visual keyword spotting (KWS) is the problem of estimating whether a tex...

2 Themos Stafylakis, et al. ∙

∙ 02/27/2018

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

Embeddings in machine learning are low-dimensional representations of co...

0 Niko Brümmer, et al. ∙

∙ 02/18/2018

End-to-end Audiovisual Speech Recognition

Several end-to-end deep learning approaches have been recently presented...

0 Stavros Petridis, et al. ∙

∙ 10/30/2017

Deep word embeddings for visual speech recognition

In this paper we present a deep learning architecture for extracting wor...

0 Themos Stafylakis, et al. ∙

∙ 03/12/2017

Combining Residual Networks with LSTMs for Lipreading

We propose an end-to-end deep learning architecture for word-level visua...

0 Themos Stafylakis, et al. ∙