Towards automatic annotation of prosodic prominence levels in Austrian German

Julian Linke, Anneliese Kelterer, Markus Alexander Dabrowski, Dina El Zarka, Barbara Schuppler

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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 languageEnglish
Title of host publicationProceedings of Speech Prosody 2020
Subtitle of host publication10th International Conference on Speech Prosody 2020
Place of PublicationTokyo, Japan
Pages1000 - 1004
DOIs
Publication statusPublished - 2020
Event10th International Conference on Speech Prosody - virtuell, Unknown
Duration: 24 May 202028 May 2020

Conference

Conference10th International Conference on Speech Prosody
Abbreviated titleSpeech Prosody 2020
CountryUnknown
Cityvirtuell
Period24/05/2028/05/20

Fingerprint Dive into the research topics of 'Towards automatic annotation of prosodic prominence levels in Austrian German'. Together they form a unique fingerprint.

  • Projects

    Prizes

    Elise Richter

    Barbara Schuppler (Recipient), Nov 2017

    Prize: Fellowship awarded competitively

    Press / Media

    Wie der Mensch von der Maschine lernt

    Barbara Schuppler & Gernot Kubin

    25/09/19

    1 Media contribution

    Press/Media: Press / Media

    Cite this

    Linke, J., Kelterer, A., Dabrowski, M. A., El Zarka, D., & Schuppler, B. (2020). Towards automatic annotation of prosodic prominence levels in Austrian German. In Proceedings of Speech Prosody 2020: 10th International Conference on Speech Prosody 2020 (pp. 1000 - 1004). Tokyo, Japan. https://doi.org/10.21437/SpeechProsody.2020-204