Marie Kunešová

Marie Kunešová

Auto-generated profile, based on publicly available information

Marie Kunešová

University of West Bohemia in Pilsen

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 July 2019
Verified
Book Chapter
Closed access
MKMarie Kunešová
Marie Kunešová
MHMarek Hruz
Marek Hruz
ZZZbyněk Zajíc
Zbyněk Zajíc
VRVlasta Radová
Vlasta Radová


10 October 2024 in International Journal of Speech Technology
Verified
Journal Article
Open access
PDF file
MKMarie Kunešová
Marie Kunešová
ZZZbyněk Zajíc
Zbyněk Zajíc
LŠLuboš Šmídl
Luboš Šmídl
MKMartin Karafiát
Martin Karafiát
The current state-of-the-art for various speech processing problems is a sequence-to-sequence model based on a self-attention mechanism known as transformer. The widely used wav2vec 2.0 is a self-supervised transformer model pre-trained on large amounts of unlabeled speech and then fine-tuned for a specific task. The data used for training and fine-tuning, along with the size of the transformer model, play a crucial role in both of these training steps. The most commonly used wav2vec 2.0 models are trained on relatively “clean” data from sources such as the LibriSpeech dataset, but we can expect there to be a benefit in using more realistic data gathered from a variety of acoustic conditions. However, it is not entirely clear how big the difference would be. Investigating this is the main goal of our article. To this end, we utilize wav2vec 2.0 models in three fundamental speech processing tasks: speaker change detection, voice activity detection, and overlapped speech detection, and test them on four real conversation datasets. We compare four wav2vec 2.0 models with different sizes and different data used for pre-training, and we fine-tune them either on in-domain data from the same dataset or on artificial training data created from the LibriSpeech corpus. Our results suggest that richer data that are more similar to the task domain bring better performance than a larger model.

13 August 2016 in Lecture Notes in Computer Science
Verified
Book Chapter
Closed access
PDF file
MHMarek Hruz
Marek Hruz
MKMarie Kunešová
Marie Kunešová

1 January 2014
Verified
Book Chapter
Closed access
PDF file
PCPavel Campr
Pavel Campr
MKMarie Kunešová
Marie Kunešová
JVJan Vaněk
Jan Vaněk
JČJan Čech
Jan Čech
JPJosef Psutka
Josef Psutka

16 September 2022
Verified
Book Chapter
Closed access
PDF file
MKMarie Kunešová
Marie Kunešová
MŘMarkéta Řezáčková
Markéta Řezáčková