Speech Analysis using Modulation-Based Features for Detecting Deception

Gopalan, K.; Wenndt, Stanley J.

doi:10.1109/icdsp.2007.4288658

Cited by 21 publications

(20 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, there have been a considerable amount of research works on deception detection in speech [6,5,7,8]. Martin Graciarena et al designed a collection paradigm to elicit within each participant deceptive and non-deceptive speech, from participants who had both financial incentive and motivation [6].…”

Section: Related Workmentioning

confidence: 99%

Construction of Chinese Deceptive Speech Detection Corpus

Cheng¹,

Zhao²,

Chen³

et al. 2015

Proceedings of the 2015 Joint International Mechanical, Electronic and Information Technology Conference

View full text Add to dashboard Cite

Nowadays, deceptive speech detection has raised more and more interests. The corpus is the foundation of researches in deceptive speech detection. While there are several corpora about English deception detection, few efforts have been put on Chinese which is quite different due to the culture divergence. In this paper, we construct a deceptive and non-deceptive Chinese speech corpus, the SUSP-DSD corpus. We first describe construction approach in detail, and then give a subjective and objective evaluation about the corpus.

show abstract

Section: Related Workmentioning

confidence: 99%

Construction of Chinese Deceptive Speech Detection Corpus

Cheng¹,

Zhao²,

Chen³

et al. 2015

Proceedings of the 2015 Joint International Mechanical, Electronic and Information Technology Conference

View full text Add to dashboard Cite

show abstract

“…Increased activation of the sympathetic nervous system or the parasympathetic nervous system is observed to occur when a speaker is upset, scared or depressed [1]. This increased activation leads to changes in heart rate, blood pressure and tremor in muscle activity [2]. In addition, the articulatory and respiratory movements for speech production are affected.…”

Section: Introductionmentioning

confidence: 99%

Deception detection in speech using bark band and perceptually significant energy features

Sanaullah

Gopalan

2013

2013 IEEE 56th International Midwest Symposium on Circuits and Systems (MWSCAS)

View full text Add to dashboard Cite

This paper presents the initial results of analysis of nonlinear spectral features for classifying truthful and deceptive speech. These features are derived on a Bark scale based on the psychoacoustic masking property of human speech perception. Truthful and deceptive speeches are established a posteriori by a male speaker under jeopardy. Test results using significant energy features at Bark bands and a neural network have a potential to show delicate variations between truthful and deceptive utterances.

show abstract

“…But, the research of speech lie detection is just at the primary and exploration stage. The problems such as the quantitative calculation of psychological acoustic features, the analysis of data fusion, the constructing of time dynamic feature model etc., all of these problems needed to be solved [9][10][11]. In recent years, the Deep Belief Network (DBN) model has been paid more attention due to its nonlinear network structure [12][13][14][15][16][17][18][19].…”

Section: Introductionmentioning

confidence: 99%

Lie Detection from Speech Analysis Based on K–SVD Deep Belief Network Model

Zhou

Zhao

Pan

2015

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Considering the task of lie detection relates some nonlinear characteristics, such as psychological acoustics and auditory perception, which are difficult to be extracted and have high computational complexity. So this paper proposes a deep belief network based on the K-singular value decomposition (K-SVD) algorithm. This method combined the multi-dimensional data linear decomposition ability of sparse algorithm and the deep nonlinear network structure of deep belief network. It is aim to extract the significant time dynamic deep lie structure characteristics. Based on these deep characteristics, the lie database of Arizona University at United States was used to test. The experimental results show that, compared with the K-SVD sparse characteristics and basic acoustic characteristics, the deep characteristics proposed in this paper has better recognition rate. Furthermore, this paper provides a new exploration for psychology calculation.

show abstract

Speech Analysis using Modulation-Based Features for Detecting Deception

Cited by 21 publications

References 3 publications

Construction of Chinese Deceptive Speech Detection Corpus

Construction of Chinese Deceptive Speech Detection Corpus

Deception detection in speech using bark band and perceptually significant energy features

Lie Detection from Speech Analysis Based on K–SVD Deep Belief Network Model

Contact Info

Product

Resources

About