On the Comparison of Different Phrase Boundary Detection Approaches Trained on Czech TTS Speech Corpora

The phrasing is a very important issue in the process of speech synthesis since it ensures higher naturalness and intelligibility of synthesized sentences. There are many different approaches to phrase boundary detection, including simple classification-based, HMM-based, CRF-based approaches, howeve...

Full description

Saved in:
Bibliographic Details
Published inSpeech and Computer Vol. 11096; pp. 255 - 263
Main Author Jůzová, Markéta
Format Book Chapter
LanguageEnglish
Published Switzerland Springer International Publishing AG 2018
Springer International Publishing
SeriesLecture Notes in Computer Science
Subjects
Classification
Conditional random fields
Neural networks
Phrase boundary
Speech corpus
Online AccessGet full text
ISBN3319995782
9783319995786
ISSN0302-9743
1611-3349
DOI10.1007/978-3-319-99579-3_27

Cover

More Information
Summary:The phrasing is a very important issue in the process of speech synthesis since it ensures higher naturalness and intelligibility of synthesized sentences. There are many different approaches to phrase boundary detection, including simple classification-based, HMM-based, CRF-based approaches, however, different types of neural networks are used for this task as well. The paper compares representative methods for phrasing of Czech sentences using large-scale TTS speech corpora as training data, taking only speaker-dependent phrasing issue into consideration.
ISBN:3319995782
9783319995786
ISSN:0302-9743
1611-3349
DOI:10.1007/978-3-319-99579-3_27