This paper aims to present an analysis of English pronunciation variations using the TIMIT corpus of American English. The manually annotated data are analyzed by comparing the pronunciation variants to their canonical pronunciations which are defined by using the CMU Pronunciation Dictionary. Vowels and consonants are separately analyzed with respect to substitution, deletion and insertion. Th...

This paper describes real user assessment of NativeAccent, a pronunciation tutor using automatic speech recognition that is a commercial product. It describes the product and discusses the issues involved in assessments of real users in real situations, such as assessments based on the customer’s own criteria instead of more academic measures, and the variations in the customers’ measures. Resu...

We automatically generate CG animations to express the pronunciation movement of speech through articulatory feature (AF) extraction to help learn a pronunciation. The proposed system uses MRI data to map AFs to coordinate values that are needed to generate the animations. By using magnetic resonance imaging (MRI) data, we can observe the movements of the tongue, palate, and pharynx in detail w...

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...

This paper describes real user assessment of NativeAccent, a pronunciation tutor using automatic speech recognition that is a commercial product. It describes the product and discusses the issues involved in assessments of real users in real situations, such as assessments based on the customer’s own criteria instead of more academic measures, and the variations in the customers’ measures. Resu...

This paper introduces a novel approach for generating multilingual text-to-phoneme mappings for use in multilingual speech recognition systems. The multilingual mappings are based on the weighted outputs from a neural network text-to-phoneme model, trained on data mixed from several languages. The multilingual mappings used together with a branched grammar decoding scheme is able to capture bot...