Detection of Prosodic Boundaries in Speech Using Wav2Vec 2.0
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F22%3A43965697" target="_blank" >RIV/49777513:23520/22:43965697 - isvavai.cz</a>
Result on the web
<a href="https://link.springer.com/chapter/10.1007/978-3-031-16270-1_31" target="_blank" >https://link.springer.com/chapter/10.1007/978-3-031-16270-1_31</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-031-16270-1_31" target="_blank" >10.1007/978-3-031-16270-1_31</a>
Alternative languages
Result language
angličtina
Original language name
Detection of Prosodic Boundaries in Speech Using Wav2Vec 2.0
Original language description
Prosodic boundaries in speech are of great relevance to both speech synthesis and audio annotation. In this paper, we apply the wav2vec 2.0 framework to the task of detecting these boundaries in speech signal, using only acoustic information. We test the approach on a set of recordings of Czech broadcast news, labeled by phonetic experts, and compare it to an existing text-based predictor, which uses the transcripts of the same data. Despite using a relatively small amount of labeled data, the wav2vec2 model achieves an accuracy of 94% and F1 measure of 83% on within-sentence prosodic boundaries (or 95% and 89% on all prosodic boundaries), outperforming the text-based approach. However, by combining the outputs of the two different models we can improve the results even further.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
20205 - Automation and control systems
Result continuities
Project
<a href="/en/project/GA21-14758S" target="_blank" >GA21-14758S: Prosodic Phrase in Current Spoken Czech: Meaning, Balance, Stochastic Patterns</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2022
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Text, Speech, and Dialogue 25th International Conference, TSD 2022, Brno, Czech Republic, September 6–9, 2022, Proceedings
ISBN
978-3-031-16269-5
ISSN
0302-9743
e-ISSN
1611-3349
Number of pages
12
Pages from-to
377-388
Publisher name
Springer International Publishing
Place of publication
Cham
Event location
Brno, Czech Republic
Event date
Sep 6, 2022
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—