Zobrazeno 1 - 9
of 9
pro vyhledávání: '"John Culnan"'
Publikováno v:
Proceedings of the Eighth Workshop on Computational Linguistics and Clinical Psychology.
Autor:
Seongjin Park, John Culnan
Publikováno v:
The Journal of the Acoustical Society of America. 150:A357-A357
The goal of the present study is to investigate whether computational models can approximate human perceptual judgments of accentedness, fluency, and comprehensibility in non-native speech using low-level acoustic features and speech rhythm features.
Autor:
John Culnan
Publikováno v:
The Journal of the Acoustical Society of America. 150:A311-A311
Autor:
Seongjin Park, John Culnan
Publikováno v:
The Journal of the Acoustical Society of America. 148:2763-2763
Autor:
Seongjin Park, John Culnan
Publikováno v:
The Journal of the Acoustical Society of America. 146:2957-2957
The aim of the present study is to investigate the performance of automatic perceptual judgment models built with neural networks. In previous studies, Franco et al. (1997) used HMM-derived scores based on posterior probabilities of phone segments, d
Autor:
Seongjin Park, John Culnan
Publikováno v:
The Journal of the Acoustical Society of America. 146:2840-2840
There are many identifiable acoustic differences between native and non-native English, including patterns of prosody (Ramirez Verdugo, 2005), vowel quality (Flege et al., 1997) and extent of reduction in speech (Baker et al., 2011), many of which ar
Autor:
Seongjin Park, John Culnan
Publikováno v:
The Journal of the Acoustical Society of America. 145:1827-1827
This study investigates differences in sentence and story production between native and non-native speakers of English for use with a system of Automatic Speech Recognition (ASR). Previous studies have shown that production errors by non-native speak
Autor:
John Culnan, Suki Yiu
Publikováno v:
The Journal of the Acoustical Society of America. 145:1911-1911
Autor:
John Culnan, Suki Yiu
Publikováno v:
The Journal of the Acoustical Society of America. 143:1967-1967
Hong Kong Cantonese is undergoing a neutralization of the labialized velar /kw/ with the plain velar /k/ before the round back vowel /ɔ/ that is well-documented auditorily but not acoustically (Bauer, 1982; Newman, 1987; To et al., 2015). The presen