Annotation Error Detection: Anomaly Detection vs. Classification

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F17%3A43932645" target="_blank" >RIV/49777513:23520/17:43932645 - isvavai.cz</a>
Result on the web
<a href="https://link.springer.com/chapter/10.1007%2F978-3-319-66429-3_13" target="_blank" >https://link.springer.com/chapter/10.1007%2F978-3-319-66429-3_13</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-319-66429-3_13" target="_blank" >10.1007/978-3-319-66429-3_13</a>

Result language
angličtina
Original language name
Annotation Error Detection: Anomaly Detection vs. Classification
Original language description
We compare two approaches to automatic detection of annotation errors in single-speaker read-speech corpora used for speech synthesis: anomaly- and classification-based detection. Both approaches principally differ in that the classification-based approach needs to use both correctly annotated and misannotated words for training. On the other hand, the anomaly-based detection approach needs only the correctly annotated words for training (plus a few misannotated words for validation). We show that both approaches lead to statistically comparable results when all available misannotated words are utilized during detector/classifier development. However, when a smaller number of misannotated words are used, the anomaly detection framework clearly outperforms the classification-based approach. A final listening test showed the effectiveness of the annotation error detection for improving the quality of synthetic speech.
Czech name
—
Czech description
—

Project
<a href="/en/project/GA16-04420S" target="_blank" >GA16-04420S: Combining phonetic and corpus-based approaches to remedy disruptive effects in synthetic speech</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year
2017
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Speech and Computer 19th International Conference, SPECOM 2017, Hatfield, UK, September 12-16, 2017, Proceedings
ISBN
978-3-319-66428-6
ISSN
0302-9743
e-ISSN
neuvedeno
Number of pages
11
Pages from-to
141-151
Publisher name
Springer
Place of publication
Cham
Event location
Hatfield, Hertfordshire, United Kingdom
Event date
Sep 12, 2017
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—

Similar results(10)