Projects per year
Abstract
The creation of prosodic annotations is one of the most diffi-cult and time-consuming aspects of creating a speech database. Generally, only the speech signal and manually created tran-scriptions are available in an early resource development stage.This paper presents a tool for annotating prosodic prominenceat the word level, using exclusively acoustic features (96 f0-,intensity- and durational features). The best performance forseparating prominent from non-prominent words in Austrianread speech was reached with a decision tree with the abso-lute word duration as the only feature. For distinguishing moreprominence levels, a good performance was reached with a ran-dom forest model, similar to the best inter-annotator agreement.Furthermore, we analyzed in detail the feature ranking of therandom forest to give us insights into the relative importanceof the features contributing to prominence in Austrian German:Word duration>f0 range, RMS range. The specific findingsof this study will mainly be relevant for speech scientists andprosody researchers interested in German. Our methodologi-cal approach of analyzing prosodic prominence from a purelyacoustic perspective at the word-level will also be interestingfor researchers focusing on prosody in other languages.
Original language | English |
---|---|
Title of host publication | Proceedings of Speech Prosody 2020 |
Subtitle of host publication | 10th International Conference on Speech Prosody 2020 |
Place of Publication | Tokyo, Japan |
Pages | 1000 - 1004 |
Number of pages | 5 |
Volume | 2020-May |
DOIs | |
Publication status | Published - 1 Jan 2020 |
Event | 10th International Conference on Speech Prosody - virtuell, Unknown Duration: 24 May 2020 → 28 May 2020 |
Publication series
Name | Proceedings of the International Conference on Speech Prosody |
---|---|
ISSN (Print) | 2333-2042 |
Conference
Conference | 10th International Conference on Speech Prosody |
---|---|
Abbreviated title | Speech Prosody 2020 |
Country/Territory | Unknown |
City | virtuell |
Period | 24/05/20 → 28/05/20 |
Keywords
- Austrian German
- Decision trees
- Prosodic features
- Prosodic prominence
- Random forests
ASJC Scopus subject areas
- Language and Linguistics
- Linguistics and Language
Fingerprint
Dive into the research topics of 'Towards automatic annotation of prosodic prominence levels in Austrian German'. Together they form a unique fingerprint.-
FWF - Spontansprache - Cross-layer language models for conversational speech
1/11/19 → 31/10/23
Project: Research project
-
FWF - CLCS_2 - Cross-layer prosodic models for conversational speech
1/10/18 → 30/11/21
Project: Research project
Prizes
Press/Media
-
Wie der Mensch von der Maschine lernt
Barbara Schuppler & Gernot Kubin
25/09/19
1 Media contribution
Press/Media: Press / Media