Construction of Chinese Deceptive Speech Detection Corpus

Cheng, Fan; Zhao, Han; Chen, Xueqin; Fan, Xingyu; Chen, Shuxi

doi:10.2991/jimet-15.2015.18

Cited by 2 publications

(2 citation statements)

References 6 publications

(7 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the spoken language Mandarin, Cheng Fan et al constructed the SUSP-DSD corpus [5,6] through a three-phase experiment designed to obtain deceptive descriptions in different scenarios; however they only used the third phase for evaluation due to the difficulties about the setting of baseline. Another limitation of their work is that the scale of the SUSP-DSD corpus is smaller when comparing with the existing English corpora.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Acoustic Indicators of Deception in Mandarin Daily Conversations Recorded from an Interactive Game

Huang¹,

Chou

Wu³

et al. 2019

Interspeech 2019

View full text Add to dashboard Cite

Being able to distinguish the differences between deceptive and truthful statements in a dialogue is an important skill in daily life. Extensive studies on the acoustic features of deceptive English speech have been reported, but such research in Mandarin is relatively scarce. We constructed a Mandarin deception database of daily dialogues from native speakers in Taiwan. College students were recruited to participate in a game in which they were encouraged to lie and convince their opponents of experiences that they did not have. After data collection, acoustic-prosodic features were extracted. The statistics of these features were calculated so that the differences between truthful and deceptive sentences, both as they were intended and perceived, can be compared. Results indicate that different people tend to use different acoustic features when telling a lie; the participants could be put into 10 categories in a dendrogram, with an exception of 31 people from whom no acoustic indicators for deception were found. Without considering interpersonal differences, our best classifier reached an F1 score of 53.37% in distinguishing deceptive and truthful segmentation units. We hope to present this new database as a corpus for future studies on deception in Mandarin conversations.

show abstract

Section: Related Workmentioning

confidence: 99%

“…A Mandarin database was constructed by collecting deceptive speech from a game [5,6]. Participants were asked to prepare either a fake or a truthful story about themselves and present it in front of two interviewers.…”

Section: Introductionmentioning

confidence: 99%