More on the normalization of syllable prominence ratings

Publikation: Beiträge in SammelwerkenAufsätze in KonferenzbändenForschungbegutachtet

Authors

The perception of syllable prominence depends to a limited extent on the acoustic properties of the speech signal in question. Psychoacoustic factors are involved as well. Thus, research often relies on two types of data: subjective prominence ratings collected in perception experiments and acoustic measures. A problem with the rating data is noise resulting from individual approaches to the rating task. This paper addresses the question of how this noise can be reduced by normalization, evaluating 12 normalization methods. In a perception experiment, prominence ratings concerning German read speech were collected. From the raw rating data 12 different 'mirror' data-sets were computed according to the 12 methods. Each mirror data-set was correlated with the same set of underlying acoustic data. The multiple regression setup included raw syllable duration as well as within syllable maximum F0 and intensity. Adjusted r 2-values could be raised considerably with selected methods.

OriginalspracheEnglisch
TitelProceedings of Interspeech 13th Annual Conference of the International Speech Communication Association : INTERSPEECH 2012, Portland, OR, 9 September 2012 - 13 September 2012, 97207
Anzahl der Seiten6
VerlagInternational Speech Communication Association
Datum2012
Seiten2415-2420
ISBN (Print)9781622767595
PublikationsstatusErschienen - 2012
Veranstaltung13th Annual Conference of the International Speech Communication Association - Interspeech 2012 - Portland, USA / Vereinigte Staaten
Dauer: 09.09.201213.09.2012
Konferenznummer: 13
https://www.isca-speech.org/archive/interspeech_2012/

Bibliographische Notiz

Paper Identifier: Thu.SS9.10