Search Results for author: Georgios Paraskevopoulos

Found 16 papers, 10 papers with code

Theano: A Greek-speaking conversational agent for COVID-19

no code implementations ACL (NLP4PosImpact) 2021 Nikoletta Ventoura, Kosmas Palios, Yannis Vasilakis, Georgios Paraskevopoulos, Nassos Katsamanis, Vassilis Katsouros

Conversational Agents (CAs) can be a proxy for disseminating information and providing support to the public, especially in times of crisis.


Regotron: Regularizing the Tacotron2 architecture via monotonic alignment loss

no code implementations28 Apr 2022 Efthymios Georgiou, Kosmas Kritsis, Georgios Paraskevopoulos, Athanasios Katsamanis, Vassilis Katsouros, Alexandros Potamianos

Recent deep learning Text-to-Speech (TTS) systems have achieved impressive performance by generating speech close to human parity.

MMLatch: Bottom-up Top-down Fusion for Multimodal Sentiment Analysis

1 code implementation24 Jan 2022 Georgios Paraskevopoulos, Efthymios Georgiou, Alexandros Potamianos

Current deep learning approaches for multimodal fusion rely on bottom-up fusion of high and mid-level latent modality representations (late/mid fusion) or low level sensory inputs (early fusion).

Multimodal Sentiment Analysis

EmpBot: A T5-based Empathetic Chatbot focusing on Sentiments

no code implementations30 Oct 2021 Emmanouil Zaranis, Georgios Paraskevopoulos, Athanasios Katsamanis, Alexandros Potamianos

Specifically, during finetuning we propose to use three objectives: response language modeling, sentiment understanding, and empathy forcing.

Chatbot Language Modelling

ADMM-DAD net: a deep unfolding network for analysis compressed sensing

1 code implementation13 Oct 2021 Vasiliki Kouni, Georgios Paraskevopoulos, Holger Rauhut, George C. Alexandropoulos

In this paper, we propose a new deep unfolding neural network based on the ADMM algorithm for analysis Compressed Sensing.

Unsupervised low-rank representations for speech emotion recognition

no code implementations14 Apr 2021 Georgios Paraskevopoulos, Efthymios Tzinis, Nikolaos Ellinas, Theodoros Giannakopoulos, Alexandros Potamianos

We examine the use of linear and non-linear dimensionality reduction algorithms for extracting low-rank feature representations for speech emotion recognition.

Dimensionality Reduction General Classification +1

Integrating Recurrence Dynamics for Speech Emotion Recognition

1 code implementation9 Nov 2018 Efthymios Tzinis, Georgios Paraskevopoulos, Christos Baziotis, Alexandros Potamianos

We investigate the performance of features that can capture nonlinear recurrence dynamics embedded in the speech signal for the task of Speech Emotion Recognition (SER).

Speech Emotion Recognition

Pattern Search Multidimensional Scaling

1 code implementation1 Jun 2018 Georgios Paraskevopoulos, Efthymios Tzinis, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Alexandros Potamianos

We present a novel view of nonlinear manifold learning using derivative-free optimization techniques.

Cannot find the paper you are looking for? You can Submit a new open access paper.