Slovak broadcast news speech recognition and transcription system

M Lojka, P Viszlay, J Staš, D Hládek, J Juhár - Advances in Network-Based …, 2019 - Springer
We have developed a working prototype of automatic subtitling system for transcription,
archiving, and indexing of Slovak audiovisual recordings, such as lectures, talks …

Influence of Highly Inflected Word Forms and Acoustic Background on the Robustness of Automatic Speech Recognition for Human–Computer Interaction

A Zgank - Mathematics, 2022 - mdpi.com
Automatic speech recognition is essential for establishing natural communication with a
human–computer interface. Speech recognition accuracy strongly depends on the …

[PDF][PDF] Word guessing game with a social robotic head

Š Beňuš, R Sabo, M Trnka - Proceedings of Information Technologies …, 2019 - ceur-ws.org
In this paper we address three limitations of our previous implementations in human-
machine spoken interaction in Slovak: low prosodic variability, limited naturalness, and …

Adding filled pauses and disfluent events into language models for speech recognition

J Staš, D Hládek, J Juhár - 2016 7th IEEE International …, 2016 - ieeexplore.ieee.org
The variation of spontaneous speech is much larger when compared to the planned speech
because of speech disruption and a lot of ambiguities in conversations. These events cannot …

[PDF][PDF] TEDxSK and JumpSK: A new Slovak speech recognition dedicated corpus

J Staš, D Hládek, P Viszlay, T Koctúr - Journal of Linguistics …, 2017 - sciendo.com
This paper describes a new Slovak speech recognition dedicated corpus built from TEDx
talks and Jump Slovakia lectures. The proposed speech database consists of 220 talks and …

Automatic transcription and subtitling of Slovak multi-genre audiovisual recordings

J Staš, P Viszlay, M Lojka, T Koctúr, D Hládek… - … for Computer Science …, 2018 - Springer
This paper summarizes a recent progress in the development of the automatic transcription
system for subtitling of the Slovak multi-genre audiovisual recordings, such as lectures, talks …

Semi-automatic processing and annotation of meeting audio recordings

S Gereg, P Viszlay, J Staš… - 2019 17th International …, 2019 - ieeexplore.ieee.org
The main theme of this article is creating a test database consisting of meeting audio
recordings. The article describes creation and experimental evaluation of proposed …

Dual-Space Re-ranking Model for Efficient Document Retrieval, User Modeling and Adaptation

J Stas, D Hládek, M Lojka… - 2018 International …, 2018 - ieeexplore.ieee.org
The increasing demand for the performance improvement and robustness of automatic
transcription of spontaneous speech in Slovak forces us to look for the advanced methods of …

[PDF][PDF] Multi-conditionally trained ASR system for reverberant speech captured by spherical microphone array in adverse acoustic conditions

P Viszlay, J Staš, M Lojka, J Greššák… - 8th Language & …, 2017 - ltc.amu.edu.pl
This paper addresses the complex problem of speech dereverberation in terms of feature
enhancement, employed in automatic speech recognition system for adverse acoustic …

Dynamic Temporal Alignment of Slovak Audiovisual Content

J Staš, M Lojka, P Viszlay, D Hládek… - 2019 17th International …, 2019 - ieeexplore.ieee.org
Access to information means power and advantage. The broadcast news is one of the
information sources, where subtitling of the live broadcast is difficult. Breaking the task into …