no code implementations • 17 Feb 2024 • Junyi Peng, Marc Delcroix, Tsubasa Ochiai, Oldrich Plchot, Shoko Araki, Jan Cernocky
We then extend a powerful TSE architecture by incorporating two SSL-based modules: an Adaptive Input Enhancer (AIE) and a speaker encoder.
no code implementations • 17 Feb 2024 • Junyi Peng, Marc Delcroix, Tsubasa Ochiai, Oldrich Plchot, Takanori Ashihara, Shoko Araki, Jan Cernocky
TSE uniquely requires both speaker identification and speech separation, distinguishing it from other tasks in the Speech processing Universal PERformance Benchmark (SUPERB) evaluation.
no code implementations • 15 Oct 2022 • Themos Stafylakis, Ladislav Mosner, Sofoklis Kakouros, Oldrich Plchot, Lukas Burget, Jan Cernocky
Self-supervised learning of speech representations from large amounts of unlabeled data has enabled state-of-the-art results in several speech processing tasks.
no code implementations • 3 Oct 2022 • Junyi Peng, Oldrich Plchot, Themos Stafylakis, Ladislav Mosner, Lukas Burget, Jan Cernocky
In recent years, self-supervised learning paradigm has received extensive attention due to its great success in various down-stream tasks.
no code implementations • 19 Mar 2022 • Anna Silnova, Themos Stafylakis, Ladislav Mosner, Oldrich Plchot, Johan Rohdin, Pavel Matejka, Lukas Burget, Ondrej Glembek, Niko Brummer
In this paper, we analyze the behavior and performance of speaker embeddings and the back-end scoring model under domain and language mismatch.
no code implementations • 6 Apr 2019 • Themos Stafylakis, Johan Rohdin, Oldrich Plchot, Petr Mizera, Lukas Burget
Contrary to i-vectors, speaker embeddings such as x-vectors are incapable of leveraging unlabelled utterances, due to the classification loss over training speakers.
no code implementations • 4 May 2014 • Ignacio Lopez-Moreno, Javier Gonzalez-Dominguez, Oldrich Plchot, David Martinez, Joaquin Gonzalez-Rodriguez, Pedro Moreno
This work studies the use of deep neural networks (DNNs) to address automatic language identification (LID).