Jindrich Matousek

ORCID

Publication Activity (10 Years)

Years Active: 1999-2024
Publications (10 Years): 52

Top Venues

Publications

Markéta Rezácková, Daniel Tihelka, Jindrich Matousek
T5G2P: Text-to-Text Transfer Transformer Based Grapheme-to-Phoneme Conversion. IEEE ACM Trans. Audio Speech Lang. Process. 32 (2024)
Jan Lehecka, Zdenek Hanzlícek, Jindrich Matousek, Daniel Tihelka
Zero-Shot vs. Few-Shot Multi-Speaker TTS Using Pre-trained Czech SpeechT5 Model. CoRR (2024)
Zdenek Hanzlícek, Jindrich Matousek, Jakub Vít
Using LSTM neural networks for cross-lingual phonetic speech segmentation with an iterative correction procedure. Comput. Intell. 40 (2) (2024)
Markéta Rezácková, Adam Frémund, Jan Svec, Jindrich Matousek
T5G2P: Multilingual Grapheme-to-Phoneme Conversion with Text-to-Text Transfer Transformer. ACPR (3) (2023)
Jindrich Matousek, Daniel Tihelka, Alice Tihelková
VITS, Tacotron or FastSpeech? Challenging Some of the Most Popular Synthesizers. ACPR (3) (2023)
Marie Kunesová, Jindrich Matousek
Neural Speech Synthesis with Enriched Phrase Boundaries. INTERSPEECH (2023)
Marie Kunesová, Jindrich Matousek, Jan Lehecka, Jan Svec, Josef Michálek, Daniel Tihelka, Martin Bulín, Zdenek Hanzlícek, Markéta Rezácková
Ensemble of Deep Neural Network Models for MOS Prediction. ICASSP (2023)
Jindrich Matousek, Daniel Tihelka
VITS: Quality Vs. Speed Analysis. TSD (2023)
Markéta Rezácková, Jindrich Matousek
Text-to-Text Transfer Transformer Phrasing Model Using Enriched Text Input. TSD (2022)
Zdenek Hanzlícek, Jindrich Matousek
Phonetic Speech Segmentation of Audiobooks by Using Adapted LSTM-Based Acoustic Models. IBERAMIA (2022)
Jindrich Matousek, Daniel Tihelka
On Comparison of Phonetic Representations for Czech Neural Speech Synthesis. TSD (2022)
Jindrich Matousek, Daniel Tihelka
Sequence-to-Sequence CNN-BiLSTM Based Glottal Closure Instant Detection from Raw Speech. ANNPR (2022)
Jindrich Matousek, Daniel Tihelka
A Comparison of Convolutional Neural Networks for Glottal Closure Instant Detection from Raw Speech. ICASSP (2021)
Michal Vrastil, Jindrich Matousek
On Comparison of XGBoost and Convolutional Neural Networks for Glottal Closure Instant Detection. TDS (2021)
Jan Volín, Markéta Rezácková, Jindrich Matousek
Human and Transformer-Based Prosodic Phrasing in Two Speech Genres. SPECOM (2021)
Daniel Tihelka, Jindrich Matousek, Alice Tihelková
How Much End-to-End is Tacotron 2 End-to-End TTS System. TDS (2021)
Daniel Tihelka, Markéta Rezácková, Martin Gruber, Zdenek Hanzlícek, Jakub Vít, Jindrich Matousek
Save Your Voice: Voice Banking and TTS for Anyone. Interspeech (2021)
Jiri Pribil, Anna Pribilová, Jindrich Matousek
Synthetic Speech Evaluation by 2D GMM Classification in Pleasure-Arousal Scale. TSP (2020)
Jirí Pribil, Anna Pribilová, Jindrich Matousek
Synthetic Speech Evaluation by Differential Maps in Pleasure-Arousal Space. SPECOM (2020)
Jindrich Matousek, Zdenek Krnoul, Michal Campr, Zbynek Zajíc, Zdenek Hanzlícek, Martin Gruber, Marie Kocurová
Speech and web-based technology to enhance education for pupils with visual impairment. J. Multimodal User Interfaces 14 (2) (2020)
Martin Gruber, Jindrich Matousek, Zdenek Hanzlícek, Daniel Tihelka
Dialogue act based expressive speech synthesis in limited domain for the Czech language. Informatica (Slovenia) 44 (2) (2020)
Jindrich Matousek, Michal Vrastil
Context-Aware XGBoost for Glottal Closure Instant Detection in Speech Signal. TDS (2020)
Jiri Pribil, Anna Pribilová, Jindrich Matousek
Artefact Determination by GMM-Based Continuous Detection of Emotional Changes in Synthetic Speech. TSP (2019)
Martin Gruber, Jakub Vít, Jindrich Matousek
Web-Based Speech Synthesis Editor. INTERSPEECH (2019)
Jindrich Matousek, Daniel Tihelka
Using Extreme Gradient Boosting to Detect Glottal Closure Instants in Speech Signal. ICASSP (2019)
Lubos Smídl, Jan Svec, Daniel Tihelka, Jindrich Matousek, Jan Romportl, Pavel Ircing
Air traffic control communication (ATCC) speech corpora and their use for ASR and TTS development. Lang. Resour. Evaluation 53 (3) (2019)
Jakub Vít, Zdenek Hanzlícek, Jindrich Matousek
Czech Speech Synthesis with Generative Neural Vocoder. TSD (2019)
Martin Gruber, Adam Chýlek, Jindrich Matousek
Framework for Conducting Tasks Requiring Human Assessment. INTERSPEECH (2019)
Jirí Pribil, Anna Pribilová, Jindrich Matousek
Evaluation of Synthetic Speech by GMM-Based Continuous Detection of Emotional States. TSD (2019)
Daniel Tihelka, Zdenek Hanzlícek, Markéta Juzová, Jindrich Matousek
First Steps Towards Hybrid Speech Synthesis in Czech TTS System ARTIC. SPECOM (2018)
Lubos Smídl, Jan Svec, Daniel Tihelka, Jindrich Matousek, Jan Romportl, Pavel Ircing
Design and Development of Speech Corpora for Air Traffic Control Training. LREC (2018)
Jindrich Matousek, Daniel Tihelka
Glottal Closure Instant Detection from Speech Signal Using Voting Classifier and Recursive Feature Elimination. INTERSPEECH (2018)
Jiri Pribil, Anna Pribilová, Jindrich Matousek
Evaluation of Synthetic Speech Quality by Statistical Analysis of Voiced and Unvoiced Part Durations. TSP (2018)
Martin Matura, Markéta Juzová, Jindrich Matousek
On the Contribution of Articulatory Features to Speech Synthesis. SPECOM (2018)
Jakub Vit, Zdenek Hanzlícek, Jindrich Matousek
On the Analysis of Training Data for Wavenet-Based Speech Synthesis. ICASSP (2018)
Jirí Pribil, Anna Pribilová, Jindrich Matousek
Automatic Evaluation of Synthetic Speech Quality by a System Based on Statistical Analysis. TSD (2018)
Daniel Tihelka, Zdenek Hanzlícek, Markéta Juzová, Jakub Vít, Jindrich Matousek, Martin Gruber
Current State of Text-to-Speech System ARTIC: A Decade of Research on the Field of Speech Technologies. TSD (2018)
Jindrich Matousek, Michal Klíma
Automatic Phonetic Segmentation Using the Kaldi Toolkit. TSD (2017)
Jindrich Matousek, Daniel Tihelka
Classification-Based Detection of Glottal Closure Instants from Speech Signals. INTERSPEECH (2017)
Jirí Pribil, Anna Pribilová, Jindrich Matousek
Automatic Classification of Types of Artefacts Arising During the Unit Selection Speech Synthesis. TSD (2017)
Martin Gruber, Jindrich Matousek, Zdenek Hanzlícek, Jakub Vít, Daniel Tihelka
WebSubDub - Experimental System for Creating High-Quality Alternative Audio Track for TV Broadcasting. INTERSPEECH (2017)
Jindrich Matousek, Daniel Tihelka
Annotation Error Detection: Anomaly Detection vs. Classification. SPECOM (2017)
Markéta Juzová, Daniel Tihelka, Jindrich Matousek, Zdenek Hanzlícek
Voice Conservation and TTS System for People Facing Total Laryngectomy. INTERSPEECH (2017)
Jindrich Matousek, Daniel Tihelka
Anomaly-based annotation error detection in speech-synthesis corpora. Comput. Speech Lang. 46 (2017)
Jiri Pribil, Anna Pribilová, Jindrich Matousek
Comparison of one and two-level architecture of the GMM-based speaker age classifier. TSP (2016)
Jindrich Matousek, Daniel Tihelka
Voting Detector: A Combination of Anomaly Detectors to Reveal Annotation Errors in TTS Corpora. INTERSPEECH (2016)
Jiri Pribil, Anna Pribilová, Jindrich Matousek
GMM-based speaker gender and age classification after voice conversion. SPLINE (2016)
Jakub Vít, Jindrich Matousek
Unit-Selection Speech Synthesis Adjustments for Audiobook-Based Voices. TSD (2016)
Martin Gruber, Jindrich Matousek, Zdenek Hanzlícek, Zdenek Krnoul, Zbynek Zajíc
ARET - Automatic Reading of Educational Texts for Visually Impaired Students. INTERSPEECH (2016)
Jindrich Matousek, Daniel Tihelka
On the Influence of the Number of Anomalous and Normal Examples in Anomaly-Based Annotation Errors Detection. TSD (2016)
Jirí Pribil, Anna Pribilová, Jindrich Matousek
Evaluation of TTS Personification by GMM-Based Speaker Gender and Age Classifier. TSD (2016)
Markéta Juzová, Daniel Tihelka, Jindrich Matousek
Designing High-Coverage Multi-level Text Corpus for Non-professional-voice Conservation. SPECOM (2016)
Jirí Pribil, Anna Pribilová, Jindrich Matousek
Experiment with GMM-Based Artefact Localization in Czech Synthetic Speech. TSD (2015)
Jindrich Matousek, Daniel Tihelka
Anomaly-based annotation errors detection in TTS corpora. INTERSPEECH (2015)
Jiri Pribil, Anna Pribilová, Jindrich Matousek
Detection of artefacts in czech synthetic speech based on ANOVA statistics. TSP (2015)
Martin Matura, Jindrich Matousek
Detection of Large Segmentation Errors with Score Predictive Model. TSD (2015)
Jirí Kala, Jindrich Matousek
Quality Improvements of Zero-Concatenation-Cost Chain Based Unit Selection. SPECOM (2014)
Daniel Tihelka, Jindrich Matousek, Zdenek Hanzlícek
Modelling F0 Dynamics in Unit Selection Based Speech Synthesis. TSD (2014)
Jiri Pribil, Anna Pribilová, Jindrich Matousek
GMM Classification of Text-to-Speech Synthesis: Identification of Original Speaker's Voice. TSD (2014)
Jirí Kala, Jindrich Matousek
Very fast unit selection using Viterbi search with zero-concatenation-cost chains. ICASSP (2014)
Martin Gruber, Jindrich Matousek
Improvements in Czech Expressive Speech Synthesis in Limited Domain. SPECOM (2013)
Milan Legát, Daniel Tihelka, Jindrich Matousek
Configuring TTS Evaluation Method Based on Unit Cost Outlier Detection. TSD (2013)
Jakub Vit, Jindrich Matousek
Concatenation Artifact Detection Trained from Listeners Evaluations. TSD (2013)
Jindrich Matousek, Daniel Tihelka, Milan Legát
Is unit selection aware of audible artifacts? SSW (2013)
Jiri Pribil, Anna Pribilová, Jindrich Matousek
Experiment with Evaluation of Quality of the Synthetic Speech by the GMM Classifier. TSD (2013)
Jindrich Matousek, Daniel Tihelka
Annotation errors detection in TTS corpora. INTERSPEECH (2013)
Jindrich Matousek, Daniel Tihelka
SVM-Based Detection of Misannotated Words in Read Speech Corpora. TSD (2013)
Zdenek Hanzlícek, Jindrich Matousek, Daniel Tihelka
Experiments on Reducing Footprint of Unit Selection TTS System. TSD (2013)
Daniel Tihelka, Zdenek Hanzlícek, Pavel Machac, Radek Skarnitzl, Jindrich Matousek
On the impact of labialization contexts on unit selection speech synthesis. ISSPIT (2012)
Jindrich Matousek, Jakub Vit
Improving automatic dubbing with subtitle timing optimisation using video cut detection. ICASSP (2012)
Jindrich Matousek, Daniel Tihelka, Lubos Smídl
On the Impact of Annotation Errors on Unit-Selection Speech Synthesis. TSD (2012)
Milan Legát, Jindrich Matousek
Identifying Concatenation Discontinuities by Hierarchical Divisive Clustering of Pitch Contours. TSD (2011)
Jindrich Matousek, Zdenek Hanzlícek, Michal Campr, Zdenek Krnoul, Pavel Campr, Martin Gruber
Web-Based System for Automatic Reading of Technical Documents for Vision Impaired Students. TSD (2011)
Milan Legát, Jindrich Matousek
Analysis of Data Collected in Listening Tests for the Purpose of Evaluation of Concatenation Cost Functions. TSD (2011)
Milan Legát, Jindrich Matousek, Daniel Tihelka
On the detection of pitch marks using a robust multi-phase algorithm. Speech Commun. 53 (4) (2011)
Jan Romportl, Jindrich Matousek
Several Aspects of Machine-Driven Phrasing in Text-to-Speech Systems. Prague Bull. Math. Linguistics 95 (2011)
Milan Legát, Jindrich Matousek
Collection and Analysis of Data for Evaluation of Concatenation Cost Functions. TSD (2010)
Jindrich Matousek
Automatic Segmentation of Parasitic Sounds in Speech Corpora for TTS Synthesis. TSD (2010)
Daniel Tihelka, Jirí Kala, Jindrich Matousek
Enhancements of viterbi search for fast unit selection synthesis. INTERSPEECH (2010)
Martin Gruber, Jindrich Matousek
Listening-Test-Based Annotation of Communicative Functions for Expressive Speech Synthesis. TSD (2010)
Jindrich Matousek
Automatic Pitch-Synchronous Phonetic Segmentation with Context-Independent HMMs. TSD (2009)
Jindrich Matousek, Radek Skarnitzl, Pavel Machac, Jan Trmal
Identification and automatic detection of parasitic speech sounds. INTERSPEECH (2009)
Milan Legát, Jindrich Matousek
Design of the Test Stimuli for the Evaluation of Concatenation Cost Functions. TSD (2009)
Zdenek Hanzlícek, Jindrich Matousek, Daniel Tihelka
First Experiments on Text-to-Speech System Personification. TSD (2009)
Jindrich Matousek, Jan Romportl
Automatic pitch-synchronous phonetic segmentation. INTERSPEECH (2008)
Jindrich Matousek, Daniel Tihelka, Jan Romportl
Building of a Speech Corpus Optimised for Unit Selection TTS Synthesis. LREC (2008)
Martin Gruber, Daniel Tihelka, Jindrich Matousek
Evaluation of various unit types in the unit selection approach for the Czech language using the Festival system. SSW (2007)
Jindrich Matousek, Jan Romportl
Recording and Annotation of Speech Corpus for Czech Unit Selection Speech Synthesis. TSD (2007)
Daniel Tihelka, Jindrich Matousek, Jirí Kala
Quality Deterioration Factors in Unit Selection Speech Synthesis. TSD (2007)
Milan Legát, Daniel Tihelka, Jindrich Matousek
Pitch Marks at Peaks or Valleys? TSD (2007)
Zdenek Hanzlícek, Jindrich Matousek
Voice Conversion Based on Probabilistic Parameter Transformation and Extended Inter-speaker Residual Prediction. TSD (2007)
Milan Legát, Jindrich Matousek, Daniel Tihelka
A robust multi-phase pitch-mark detection algorithm. INTERSPEECH (2007)
Zdenek Hanzlícek, Jindrich Matousek
F0 transformation within the voice conversion framework. INTERSPEECH (2007)
Daniel Tihelka, Jindrich Matousek
Diphones vs. Triphones in Czech Unit Selection TTS. TSD (2006)
Milos Zelezný, Zdenek Krnoul, Petr Císar, Jindrich Matousek
Design, implementation and evaluation of the Czech realistic audio-visual speech synthesis. Signal Process. 86 (12) (2006)
Jindrich Matousek, Daniel Tihelka, Jan Romportl
Current State of Czech Text-to-Speech System ARTIC. TSD (2006)
Daniel Tihelka, Jindrich Matousek
Unit selection and its relation to symbolic prosody: a new approach. INTERSPEECH (2006)
Zdenek Hanzlícek, Jindrich Matousek
First Steps Towards New Czech Voice Conversion System. TSD (2006)
Jindrich Matousek, Jan Romportl
On building phonetically and prosodically rich speech corpus for text-to-speech synthesis. Computational Intelligence (2006)
Jan Romportl, Jindrich Matousek
Formal Prosodic Structures and Their Application in NLP. TSD (2005)

Jindrich Matousek.css-eqlu8i{font-size:small;padding-left:4px;}

Publication Activity (10 Years)

Top Topics

Top Venues

Jindrich Matousek