作者: Mitchell Peabody , Stephanie Seneff
DOI:
关键词:
摘要: Native speakers of non-tonal languages, such as American English, frequently have difficulty accurately producing the tones Mandarin Chinese. This paper describes a corpus Chinese spoken by non-native and annotated for tone quality using simple good/bad system. We examine interrater correlation annotations highlight differences in feature distribution between native, good non-native, bad productions. find that features judged majority to be are significantly different from good, produced native speakers.