1. Introduction This study aims at developing an automated pronunciation scoring method for second language learners of English (Hereafter, L2 learners) using both confidence scoring and classifiers. The pronunciation errors have been detected using the confidence measure from speech recognition [Franco et al. However, the accuracy of the assessment based on the confidence scores is not always ...

The current study assessed whether overhearing Spanish during childhood helps later Spanish pronunciation in adulthood. Our preliminary report based on a subset of the data [Au et al., Psychol. Sci. 13, 238-243 (2002)] revealed that adults who overheard Spanish during childhood had better Spanish pronunciation, but not better morphosyntax, than adult learners of Spanish who had no childhood exp...

L2 speech is often characterized by deviations from standard pronunciation leading native speakers to rate non native speakers as foreigners and to develop discriminatory attitudes against them [1]. Foreign accent reduction would therefore facilitate communication in the modern multilingual societies. Several studies on L2 acquisition and on speech synthesis have emphasized the role of supraseg...

This research is aimed at analyzing and improving automatic pronunciation error detection in a second language. Dutch vowels spoken by adult non-native learners of Dutch are used as a test case. A first study on Dutch pronunciation by L2 learners with different L1s revealed that vowel pronunciation errors are relatively frequent and often concern subtle acoustic differences between the realizat...

In this paper, we present an acoustic-phonetic approach to automatic pronunciation error detection. Classifiers using techniques such as Linear Discriminant Analysis or a decision tree were developed for three sounds that are frequently pronounced incorrectly by L2-learners of Dutch: /A/, /Y/ and /x/. The acoustic properties of these pronunciation errors were examined so as to define a number o...

Estonian and Finnish are closely related languages both exploiting duration cues contrastively; however, the quantity systems in the two languages are different. The Estonian quantity system involves three contrastive patterns referred to as short (Q1), long (Q2) and overlong (Q3) quantity degrees. These contrasts are manifested by a complex interaction of durational and tonal cues in a disylla...

Seventeen French-English bilinguals read aloud a set of English sentences and performed an ABX discrimination task that assessed their perception of the English / /-/i/ contrast. Global nativelikeness in production correlated with pronunciation accuracy for the vowels / / and /i/, and both production measures correlated with self-estimated pronunciation skills. However, performance on the perce...

A system for providing Computer Assisted Pronunciation Training for Dutch was developed, Dutch-CAPT, which appeared to be effective in improving pronunciation quality of L2 learners of Dutch. In this paper we describe the architecture of the system paying particular attention to the rationale behind this system, to the performance of the error detection algorithm and its relationship to the ped...

This paper examines the vowel production of eight young male speakers of Mäori in order to assess whether there are pronunciation differences between those who were raised as L1 speakers of Mäori and those who clearly learnt English first. We demonstrate that the L1 speakers produce two vowel pairs, /a:/ (WÄ), /a/ (WAKA) and /ü:/ (TÜ), /u/ (TUKU) significantly farther back than the L2 speakers....

In this paper we report on a study on pronunciation errors by Spanish learners of Dutch, which was aimed at obtaining information to develop a dedicated Computer Assisted Pronunciation Training (CAPT) program for this fixed language pair (Spanish L1, Dutch L2). The results of our study indicate, that, first, vowel errors are more frequent and variable than consonant mispronunciations. Second, S...