Dissemin is shutting down on January 1st, 2025

Published in

Interspeech 2012, 2012

DOI: 10.21437/interspeech.2012-250

Links

Tools

Export citation

Search in Google Scholar

The Automatic Assessment of Non-native Prosody: Combining Classical Prosodic Analysis with Acoustic Modelling

Proceedings article published in 2012 by Florian Hönig, Tobias Bocklet, Korbinian Riedhammer, Anton Batliner, Elmar Nöth ORCID
This paper is available in a repository.
This paper is available in a repository.

Full text: Download

Question mark in circle
Preprint: policy unknown
Question mark in circle
Postprint: policy unknown
Question mark in circle
Published version: policy unknown

Abstract

In earlier studies, we employed a large prosodic feature vec-tor to assess the quality of L2 learner's utterances with respect to sentence melody and rhythm. In this paper, we combine these features with two standard approaches in paralinguistic analysis: (1) features derived from a Gaussian Mixture Model used as Universal Background Model (GMM-UBM), and (2) openSMILE, an open-source toolkit for extracting acoustic fea-tures. We evaluate our approach with English speech from 94 non-native speakers perceptually scored by 62 native labellers. GMM-UBM or openSMILE modelling alone yields lower per-formance than our prosodic feature vector; however, adding in-formation from the GMM-UBM modelling or openSMILE by late fusion improves results.