Automatic Analysis of Speech Prosody in Dutch

Abstract

In this paper we present a publicly available tool for automatic analysis of speech prosody (AASP) in Dutch. Incorporating the state-of-the-art analytical frameworks, AASP enables users to analyze prosody at two levels from different theoretical perspectives. Holistically, by means of the Functional Principal Component Analysis (FPCA) it generates mathematical functions that capture changes in the shape of a pitch contour. The tool outputs the weights of principal components in a table for users to process in further statistical analysis. Structurally, AASP analyzes prosody in terms of prosodic events within the auto-segmental metrical framework, hypothesizing prosodic labels in accordance with Transcription of Dutch Intonation (ToDI) with accuracy comparable to similar tools for other languages. Published as a Docker container, the tool can be set up on various operating systems in only two steps. Moreover, the tool is accessed through a graphic user interface, making it accessible to users with limited programming skills.

A proposal for research on the acquisition of prosodic focus marking in diverse languages: A response to Kidd and Garcia (2022)

“…Sessions are recorded using a digital recorder at a sample rate and bit depth of 44.l kHz/16-bit, and can be further processed using Praat (Boersma, 2001). In order to position prosodic focus marking analysis within the target language's prosodic system, researchers can employ phonologically-oriented notations proposed within the autosegmental-metrical framework (AM) (Jun, 2005(Jun, , 2014Gussenhoven & Chen, 2020). If this is not feasible, researchers can conduct acoustic analyses on the use of F0-, duration-, and intensity-related cues (Lee et al, 2015) and model shapes of F0 contours (Turco et al, 2011).…”

“…Examples of applying AM-based notations to children’s productions are reviewed in Chen et al (2020). Tools for AM-based automatic transcription of intonation are available for English (Rosenberg, 2010), Spanish and Catalan (Elvira-García et al, 2016), and Dutch (Hu et al, 2020), and may be applied to child speech. Acoustic analyses on the use of prosodic parameters and modeling of F0 contours can be conducted semi-automatically, for example, via ProsodyPro (Xu, 2013) and AASP (Hu et al, 2020), respectively.…”

“…Tools for AM-based automatic transcription of intonation are available for English (Rosenberg, 2010), Spanish and Catalan (Elvira-García et al, 2016), and Dutch (Hu et al, 2020), and may be applied to child speech. Acoustic analyses on the use of prosodic parameters and modeling of F0 contours can be conducted semi-automatically, for example, via ProsodyPro (Xu, 2013) and AASP (Hu et al, 2020), respectively. These resources and research initiatives can be coordinated by establishing collaborative projects (cf.…”