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

  • In earlier studies, we assessed the degree of non-nativeness employing prosodic information. In this paper, we combine prosodic information with (1) features derived from a Gaussian Mixture Model used as Universal Background Model (GMM-UBM), a powerful approach used in speaker identification, and (2) openSMILE, a standard open-source toolkit for extracting acoustic features. We evaluate our approach with English speech from 94 non-native speakers. GMM-UBM or openSMILE modelling alone yields lower performance than our prosodic feature vector; however, adding information from the GMM-UBM modelling or openSMILE by late fusion improves results.

Export metadata

Additional Services

Search Google Scholar
Author:Florian Hönig, Tobias Bocklet, Korbinian Riedhammer, Anton Batliner, Elmar Nöth
Parent Title (English):INTERSPEECH 2012, 13th Annual Conference of the International Speech Communication Association (ISCA), Portland, OR, USA, September 2012.
Document Type:Conference Proceeding
Publication Year:2012
Tag:automatic assessment
computer-assisted language learning; non-native prosody; rhythm
faculties / departments:Fakultät für Informatik
Dewey Decimal Classification:0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme / 000 Informatik, Informationswissenschaft, allgemeine Werke