Automatic Assessment of Prosody in Second Language Learning
Florian Hönig
Diese Publikation zitieren
Florian Hönig, Automatic Assessment of Prosody in Second Language Learning (2017), Logos Verlag, Berlin, ISBN: 9783832592639
Beschreibung / Abstract
Worldwide there is a universal need for second language language learning. It is obvious that the computer can be a great help for this, especially when equipped with methods for automatically assessing the learner's pronunciation. While assessment of segmental pronunciation quality (i. ,e. whether phones and words are pronounced correctly or not) is already available in commercial software packages, prosody (i.e. rhythm, word accent, etc.) is largely ignored---although it highly impacts intelligibility and listening effort.
The present thesis contributes to closing this gap by developing and analyzing methods for automatically assessing the prosody of non-native speakers. We study the detection of word accent errors and the general assessment of the appropriateness of a speaker's rhythm. We propose a flexible, generic approach that is (a) very successful on these tasks, (b) competitive to other state-of-the-art result, and at the same time (c) flexible and easily adapted to new tasks.
The present thesis contributes to closing this gap by developing and analyzing methods for automatically assessing the prosody of non-native speakers. We study the detection of word accent errors and the general assessment of the appropriateness of a speaker's rhythm. We propose a flexible, generic approach that is (a) very successful on these tasks, (b) competitive to other state-of-the-art result, and at the same time (c) flexible and easily adapted to new tasks.
Inhaltsverzeichnis
- BEGINN
- 1 Introduction
- 1.1 Motivation
- 1.2 Prosody
- 1.3 Second language learning
- 1.4 Computer-assisted language learning
- 1.5 Contribution of this work
- 1.6 Structure of this work
- 2 The role of prosody in first and second language
- 2.1 Prosody in first language
- 2.2 Prosody in second language acquisition
- 3 Automatic assessment of prosody: state of the art
- 3.1 Analysis of prosodic events
- 3.2 Assessment of rhythm in a second language
- 4 Mathematical and technological foundations
- 4.1 Acoustic short-time features
- 4.2 Classification by parametric density estimation
- 4.3 Support vector machines
- 4.4 Support vector regression
- 4.5 Hidden markov models
- 5 Corpora
- 5.1 C-AuDiT
- 5.2 AUWL
- 6 Annotation
- 6.1 C-AuDiT
- 6.2 AUWL
- 6.3 Inter-rater agreement
- 7 Modelling of prosody
- 7.1 Features
- 7.2 Classification and regression
- 8 Experimental results
- 8.1 Segmentation
- 8.2 Word accent position
- 8.3 Rhythm
- 9 Discussion
- 10 Summary
- A Corpora details
- List of Figures
- List of Tables
- Bibliography