Google speech recognition of an English paragraph produced by Korean college students in clear or casual speech styles

2018 ◽  
Vol 143 (3) ◽  
pp. 1870-1870
Author(s):  
Byunggon Yang
2020 ◽  
Vol 67 (5) ◽  
pp. 568-579 ◽  
Author(s):  
Haram J. Kim ◽  
Shin Ye Kim ◽  
Ryan D. Duffy ◽  
Nguyen P. Nguyen ◽  
Danni Wang

2020 ◽  
Vol 2 (2) ◽  
Author(s):  
Yaru Wu ◽  
Martine Adda-Decker ◽  
Lori Lamel
Keyword(s):  

This study aims to analyse factors that could influence schwa deletion in word-initial syllables of polysyllabic words in continuous French speech. Both phonological and extralinguistic factors were considered: number of consonants, post-lexical context, speech style, sex and profession. Three large corpora covering different speech styles were explored using forced alignment with optional schwa variants. Formal journalistic ESTER corpus, conversational journalistic ETAPE corpus and casual speech NCCFr corpus were used in this study. We observe that schwa tends to be deleted more for 2C-words than for 3C-words. Words preceded by a consonant or a pause tend to prevent schwa deletion whereas words preceded by a vowel tend to facilitate schwa deletion. The less formal the speech style is, the more schwas are deleted. Males tend to delete schwas more frequently than females. Interestingly, journalists tend to delete more schwas than politicians in our data.


Sign in / Sign up

Export Citation Format

Share Document