no code implementations • LREC 2022 • Dimitrios Roussis, Vassilis Papavassiliou, Prokopis Prokopidis, Stelios Piperidis, Vassilis Katsouros
This paper presents SciPar, a new collection of parallel corpora created from openly available metadata of bachelor theses, master theses and doctoral dissertations hosted in institutional repositories, digital libraries of universities and national archives.
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.
1 code implementation • 21 Sep 2023 • Theodoros Kouzelis, Vassilis Katsouros
Our approach leverages the similarity between audio and text embeddings in CLAP.
1 code implementation • 20 Sep 2023 • Manos Plitsis, Theodoros Kouzelis, Georgios Paraskevopoulos, Vassilis Katsouros, Yannis Panagakis
In this work, we investigate the personalization of text-to-music diffusion models in a few-shot setting.
1 code implementation • 30 May 2023 • Theodoros Kouzelis, Georgios Paraskevopoulos, Athanasios Katsamanis, Vassilis Katsouros
The study of speech disorders can benefit greatly from time-aligned data.
no code implementations • 31 Dec 2022 • Georgios Paraskevopoulos, Theodoros Kouzelis, Georgios Rouvalis, Athanasios Katsamanis, Vassilis Katsouros, Alexandros Potamianos
Modern speech recognition systems exhibits rapid performance degradation under domain shift.
no code implementations • 28 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.
no code implementations • 1 Apr 2022 • Gerasimos Chatzoudis, Manos Plitsis, Spyridoula Stamouli, Athanasia-Lida Dimou, Athanasios Katsamanis, Vassilis Katsouros
Like in many medical applications, aphasic speech data is scarce and the problem is exacerbated in so-called "low resource" languages, which are, for this task, most languages excluding English.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2