2009
DOI: 10.1016/j.specom.2009.05.007
|View full text |Cite
|
Sign up to set email alerts
|

Comparing different approaches for automatic pronunciation error detection

Abstract: International audienceOne of the biggest challenges in designing computer assisted language learning (CALL) applications that provide automatic feedback on pronunciation errors consists in reliably detecting the pronunciation errors at such a detailed level that the information provided can be useful to learners. In our research we investigate pronunciation errors frequently made by foreigners learning Dutch as a second language. In the present paper we focus on the velar fricative // and the velar plosive /k/… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
73
0
2

Year Published

2012
2012
2019
2019

Publication Types

Select...
5
3
1

Relationship

0
9

Authors

Journals

citations
Cited by 103 publications
(75 citation statements)
references
References 9 publications
(21 reference statements)
0
73
0
2
Order By: Relevance
“…In the context of pronunciation instruction, researchers propose using ASR to teach the pronunciation of a foreign language and to assess students' oral production. While many studies show that ASR technology can be effective for the teaching of segments [35][36][37][38][39][40][41], there is a lack of research reporting on learners' perceptions of using such tools.…”
Section: Automatic Speech Recognition and Effects On L2 Learningmentioning
confidence: 99%
“…In the context of pronunciation instruction, researchers propose using ASR to teach the pronunciation of a foreign language and to assess students' oral production. While many studies show that ASR technology can be effective for the teaching of segments [35][36][37][38][39][40][41], there is a lack of research reporting on learners' perceptions of using such tools.…”
Section: Automatic Speech Recognition and Effects On L2 Learningmentioning
confidence: 99%
“…Il est probable qu'il s'agisse plutôt de dévoisement, c'est pourquoi nous avons également ajouté 3 obstruantes non voisées [f s ʃ] dans le même contexte vocalique et syntaxique, uniquement en tâche de lecture, afin de pouvoir étudier ce type de production également. En effet, rappelons que les obstruantes en position finale dans la syllabe sont sujettes au dévoisement en allemand, mais pas en français (par exemple Wiese, 1996ou Möbius, 2004. Rappelons que le trait phonologique dit de « voisement » qui oppose les obstruantes voisées aux obstruantes non voisées ne repose pas que sur la caractéristique articulatoire de voisement (vibration des plis vocaux).…”
Section: Corpus 21 Constitution Du Corpusunclassified
“…Ce corpus, grâce à un nouvel inventaire des prononciations déviantes produites par des locuteurs non natifs, devrait donc permettre à terme d'améliorer le système d'alignement automatique sur de la parole non native. Rappelons que la détection et la correction des erreurs (qui font partie intégrante de l'apprentissage des langues assisté par ordinateur, cadre dans lequel s'inscrit notre projet) s'appuient sur la reconnaissance automatique de la parole ou sur les méthodes de classification (voir par exemple Witt & Young, 2000;Strik et al, 2009). …”
Section: Introductionunclassified
“…Strik et. al [13] extracted acoustic-phonetic features and applied linear discriminant analysis (LDA), while Wei et. al [14] considered log-likelihood ratios (LLR) between the canonical phone model and a set of pronunciation variation models, and used support vector machine (SVM) for classification.…”
Section: Related Workmentioning
confidence: 99%