Projects of Department of Cybernetics & NTIS P1 - Cybernetic Systems, University of West Bohemia

The following paper was accepted for SPECOM 2017 conference (indexed by ISI Web of Knowledge and Scopus):

• MATOUŠEK, J., TIHELKA, D. Annotation Error Detection: Anomaly Detection vs. Classification (Research Area RA1: Activity RA1d)

The following three papers were accepted for TSD 2017 conference (indexed by ISI Web of Knowledge and Scopus):

• JŮZOVÁ, M., TIHELKA, D., SKARNITZL, R. Last Syllable Unit Penalization in Unit Selection TTS (Research Area RA3: Activity RA3d)
• HANZLÍČEK, Z. Optimal Number of States in HMM-Based Speech Synthesis (RA4: RA4b)
• PŘIBIL, J., PŘIBILOVÁ, A., MATOUŠEK, J. Automatic Classification of Types of Artefacts Arising During the Unit Selection Speech Synthesis (RA4: R4a)

The following article has been accepted for publication in the journal Computer Speech and Language (ISSN: 0885-2308, IF: 1.324)

• MATOUŠEK, J., TIHELKA, D. Anomaly-based annotation error detection in speech-synthesis corpora (Research Area RA1: Activity RA1d)

The following article was published in the Journal of Electrical Engineering (Volume 68, 2017, ISSN 1335-3632, IF 0.407, DOI: https://doi.org/10.1515/jee-2017-0001)

• PŘIBIL, J., PŘIBILOVÁ, A., MATOUŠEK, J. GMM-based speaker age and gender classification in Czech and Slovak (Research Area RA4: Activity RA4a)

Project meeting at the Institute of Phonetics, Faculty of Arts and Philosophy, Charles University in Prague.

31.1. 2017 proběhla na půdě Západočeské univerzity v Plzni pracovní schůzka partnerů projektu.

Veřejná stránka projektu spuštěna

The following paper was accepted for prestigious INTERSPEECH 2016 conference (indexed by ISI Web of Knowledge and Scopus):

• MATOUŠEK, J., TIHELKA, D. Voting Detector: A Combination of Anomaly Detectors to Reveal Annotation Errors in TTS Corpora (RA1: RA1d)

The following paper was accepted for SPECOM 2016 conference (indexed by ISI Web of Knowledge and Scopus):

• TIHELKA, D., GRŮBER, M., JŮZOVÁ, M. Experiments with One—Class Classifier as a Predictor of Spectral Discontinuities in Unit Concatenation (RA4: RA4a)

The following four papers were accepted for TSD 2016 conference (indexed by ISI Web of Knowledge and Scopus):

• MATOUŠEK, J., TIHELKA, D. On the Influence of the Number of Anomalous and Normal Examples in Anomaly-Based Annotation Errors Detection (Research Area RA1: Activity RA1d)
• HANZLÍČEK, Z. Correction of prosodic phrases in large speech corpora (RA1: RA1d)
• PŘIBIL, J., PŘIBILOVÁ, A., MATOUŠEK, J. GMM-based Speaker Age and Gender Classification in Czech and Slovak (RA4: R4a)
• BOŘIL, T., SKARNITZL, R. Tools rPraat and mPraat: Interfacing phonetic analyses with signal processing (RA1: RA1a, RA1b, RA1c)