It is notoriously difficult to evaluate L2 prosody objectively, since there is little consensus as to what constitutes a correct prosody for a given utterance. This presentation describes an automatic procedure which consists in comparing a non-native speakers production with 10 instances of the same utterance, taken from the OMProDat database, and read by native speakers. The pitch and relativ...

The goal of the present paper is to study interference between French and English prosody. In order to study the influence of the prosody on the second language pronunciation, F0 slopes and vowel durations of the last syllables of prosodic groups were measured and analyzed in the pronunciation of French native speakers speaking French and English, and of English native speakers speaking English...

The goal of the present paper is to study interference between French and English prosody. In order to study the influence of the prosody on the second language pronunciation, F0 slopes and vowel durations of the last syllables of prosodic groups were measured and analyzed in the pronunciation of French native speakers speaking French and English, and of English native speakers speaking English...

Context speaking rate is an important cue in spoken-word recognition in a speaker’s native language [1], [2]. Native speakers entrain to the context rate; when they encounter ambiguous regions of speech, native speakers perceive fewer words and/or syllables when the surrounding speaking material is presented a relatively slow rate than when presented with a relatively fast context speaking rate...

Significant work is being done to develop NLP systems that can detect writing errors produced by non-native English speakers. A major issue, however, is the lack of available error-annotated training data needed to build statistical models that drive these major systems. As a result, many systems are trained on well-formed text with no modeling of typical errors that non-native speakers produce...

Information on what kinds of mispronunciation cause the greatest loss in naturalness can be used in guidance to help learners achieve their goals of speaking with good pronunciation. We recorded Japanese words spoken by bilinguals in Tokyo Japanese and in foreign accents (English and Korean) and morphed them together with STRAIGHT emphasizing different acoustic parameters. By using STRAIGHT, we...

This paper presents the SINOD database, which is the first Slovenian non-native speech database. It will be used to improve the performance of large vocabulary continuous speech recogniser for non-native speakers. The main quality impact is expected for acoustic models and recogniser’s vocabulary. The SINOD database is designed as supplement to the Slovenian BNSI Broadcast News database. The sa...

In speech technology, we found several challenges in automatic speech transcription system for multilingual conferences or meetings. Firstly, the dialog occurs between native and non-native speakers. Secondly, the non-native speakers come from different parts of the world (e.g., English spoken by native French speakers or English spoken by native Vietnamese speakers, etc.). Thirdly, no data or ...

The development of automatic speech recognition systems poses several known difficulties. One of them concerns the recognizer’s accuracy when dealing with non-native speakers of a given language. Normally a recognizer precision is lower for non-native users, hence our goal is to improve this low accuracy rate when the speech recognition system is confronted with a foreign accent. A typical usag...