Physiological Signals and Their Use in Augmenting Emotion Recognition for Human–Machine Interaction

Knapp, Raymond; Kim, Jong-Hwa; André, Elisabeth

doi:10.1007/978-3-642-15184-2_9

Cited by 42 publications

(19 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Even early works on multimodal emotion recognition had already been published, such as Tartter [640], although it should be mentioned that his classifiers were humans. Recently, a concise review appeared [352], which briefly wraps up some key notions of affective computing. They report 92% correct classification rate as best result, using (only) 4 signals and discriminating between 4 emotions.…”

Section: A Reviewmentioning

confidence: 99%

Affective signal processing (ASP) : unraveling the mystery of emotions

Broek¹

View full text Add to dashboard Cite

Section: A Reviewmentioning

confidence: 99%

Affective signal processing (ASP) : unraveling the mystery of emotions

Broek¹

View full text Add to dashboard Cite

“…Often these measurements have been used as indicators of emotional state [53]. In relation to music, these measurements have been used both to gauge an audience's reaction to a piece of music [25] [37] as well as a means for people to play their own music [54] [82].…”

Section: Measuring Complexity From Physiological Signalsmentioning

confidence: 99%

Musiplectics: computational assessment of the complexity of music scores

Holder

Tilevich

Gillick

2015

2015 ACM International Symposium on New Ideas, New Paradigms, and Reflections on Programming and Software (Onward!)

View full text Add to dashboard Cite

In the Western classical tradition, musicians play music from notated sheet music, called a score. When playing music from a score, a musician translates its visual symbols into sequences of instrument-specific physical motions. Hence, a music score's overall complexity represents a sum of the cognitive and mechanical acuity required for its performance. For a given instrument, different notes, intervals, articulations, dynamics, key signatures, and tempo represent dissimilar levels of difficulty, which vary depending on the performer's proficiency. Individual musicians embrace this tenet, but may disagree about the degrees of difficulty. This thesis introduces musiplectics1 , a systematic and objective approach to computational assessment of the complexity of a music score for any instrument. Musiplectics defines computing paradigms for automatically and accurately calculating the complexity of playing a music score on a given instrument. The core concept codifies a two-phase process. First, music experts rank the relative difficulty of individual musical components (e.g., notes, intervals, dynamics, etc.) for different playing proficiencies and instruments. Second, a computing engine automatically applies this ranking to music scores and calculates their respective complexity. As a proof of concept of musiplectics, we present an automated, Web-based application called Musical Complexity Scoring (MCS) for music educators and performers. Musiplectics can engender the creation of practical computing tools for objective and expeditious assessment of a music score's suitability for the abilities of intended performers.This thesis is based on research submitted for publication at ONWARD'15.That this work received support from a Virginia Tech ICAT SEAD grant.1 musiplectics = music + plectics, Greek for the study of complexity DedicationTo the memory of Coppertone Holder, the standard by which all other pets shall be measured.iii Acknowledgments I have not experienced anything in this world quite like the publication of my master's thesis. It has taken only my last two years of graduate school to accomplish, but it has brought me (kicking and screaming at times) further along in those two years than I could have possibly imagined. This process took its toll many times not only on myself, but on all of those close to me. Thus, I'd like to take a moment to graciously acknowledge and thank all of those that had a hand in both shaping my research and keeping my sanity.

show abstract

“…Later Farwell discovered the MERMER ("Memory and Encoding Related Multifaceted Electroencephalographic Response") [3], which include P300 and some additional features. Brain-based lie detector is different from the polygraph, which measures emotion-based physiological signals such as heart rate, sweating, and blood pressure [4]. Also, unlike polygraph testing, it does not attempt to determine whether or not the subject is lying or telling the truth.…”

Section: Eeg Based Lie Detection In Forensic Sciencementioning

confidence: 99%

Criminal forensic: An application to EEG

Mohanchandra

2015

2015 Recent and Emerging Trends in Computer and Computational Sciences (RETCOMP)

View full text Add to dashboard Cite

In the recent years, especially during the last decade electroencephalography (EEG) based brain computer interface (BCI) have become a prevailing study of neuroscience, machine learning and rehabilitation. A BCI provides an arena for a human brain to communicate with a computer directly without the normal neurophysiologic pathways. The electrical signals of the brain, with their fast responsivity with cognitive processes are most suitable as non-motor control mediation between the human and a computer. This can serve as a communication and control channel for various applications. One of the most intriguing uses of EEG is in forensic investigation, used as a tool in lie detection. Lie detection technology has been applied increasingly to investigate and solve criminal cases. Though the contributions of neurobiological research to forensic technology remain largely hypothetical, the evidences appear promising and further research is both feasible and warranted. The brain based lie detection may veritably give solution to many complicated investigation. This paper explores the evolvement of lie detection technology, their working principles, the latest development, and the prospect of their application in forensic science.

show abstract

Physiological Signals and Their Use in Augmenting Emotion Recognition for Human–Machine Interaction

Cited by 42 publications

References 36 publications

Affective signal processing (ASP) : unraveling the mystery of emotions

Affective signal processing (ASP) : unraveling the mystery of emotions

Musiplectics: computational assessment of the complexity of music scores

Criminal forensic: An application to EEG

Contact Info

Product

Resources

About