Intonation classification for L2 English speech using multi-distribution deep neural networks. (May 2017)

• Record Type: Journal Article
• Authors: Li, Kun; Wu, Xixin; Meng, Helen
• Is Part Of: Computer speech & language. Volume 43(2017)
• Page Start: 18
• Page End: 33
• Publication Date: 2017-05
• Subjects: Language learning -- L2 English speech -- Suprasegmental -- Intonation -- Pitch accent -- Deep neural networks; Speech processing systems -- Periodicals; Automatic speech recognition -- Periodicals; Computers -- Periodicals; Linguistics -- Periodicals; Speech-Language Pathology -- Periodicals; Traitement automatique de la parole -- Périodiques; Reconnaissance automatique de la parole -- Périodiques; Automatic speech recognition; Speech processing systems; Electronic journals; Periodicals; 006.454
• DOI: 10.1016/j.csl.2016.11.006
• Languages: English
• ISSNs: 0885-2308

Abstract

Highlights: An automatic intonation classifier for L2 English speech is proposed RULF labels are proposed to transcribe an intonation as rising, upper, lower or falling Pitch contour from final pitch accent to the end of intonational phrase(IP) is important for intonation classification Intonation classifier works well, even if we only consider 8 frames of pitch values prior to the end of pitch contour Abstract: This paper investigates the use of multi-distribution deep neural networks (MD-DNNs) for automatic intonation classification in second-language (L2) English speech. If a classified intonation is different from the target one, we consider that mispronunciation is detected and appropriate diagnostic feedback can be provided thereafter. To transcribe speech data for intonation classification, we propose the RULF labels which are used to transcribe an intonation as rising, upper, lower or falling . These four types of labels can be further merged into two groups – rising and falling . Based on the annotated data from 100 Mandarin and 100 Cantonese learners, we develop an intonation classifier, which considers only 8 frames (i.e., 80 ms) of pitch value prior to the end of the pitch contour over an intonational phrase (IP). This classifier determines the intonation of L2 English speech as either rising or falling with an accuracy of 93.0%.