2008
DOI: 10.1109/icassp.2008.4518041
|View full text |Cite
|
Sign up to set email alerts
|

Speech-based cognitive load monitoring system

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
2

Citation Types

3
91
0

Year Published

2009
2009
2020
2020

Publication Types

Select...
5
1

Relationship

3
3

Authors

Journals

citations
Cited by 75 publications
(94 citation statements)
references
References 5 publications
3
91
0
Order By: Relevance
“…The major challenge of choosing the assessment features for automated cognitive load detection is to make sure they satisfy the requirements of consistency, compact representation and automatic acquisition [98]. Cognitive load measurement approaches aim to find effective features which reliably reflect the cues and can be extracted automatically such that they are useful in adaptive systems.…”
Section: Estimating Load From Interactive Behaviormentioning
confidence: 99%
See 1 more Smart Citation
“…The major challenge of choosing the assessment features for automated cognitive load detection is to make sure they satisfy the requirements of consistency, compact representation and automatic acquisition [98]. Cognitive load measurement approaches aim to find effective features which reliably reflect the cues and can be extracted automatically such that they are useful in adaptive systems.…”
Section: Estimating Load From Interactive Behaviormentioning
confidence: 99%
“…Cognitive load measurement approaches aim to find effective features which reliably reflect the cues and can be extracted automatically such that they are useful in adaptive systems. They also aim to find a suitable learning or modeling scheme for each index in order to resolve the corresponding level of cognitive load [98]. By manipulating the level of task complexity and cognitive load, and conducting a series of repeated measures user studies in a variety of scenarios, it has been able to identify a series of cognitive load indices based on features from a number of input modalities, specifically, observations of significant changes in speech and digital-pen input that are abstracted from individual application domains in which they occur as well as correlated to high cognitive load.…”
Section: Estimating Load From Interactive Behaviormentioning
confidence: 99%
“…pitch, prosody, pauses, and disfluencies, have also been found to be changing under high levels of CL [4,[8][9][10]. Such measures allow non-intrusive analysis as they are based on speech data generated by users while they complete the task.…”
Section: Introductionmentioning
confidence: 99%
“…Speech processing offers the ability to monitor cognitive workload in a non-intrusive way, compared to measures such as blood pressure, heart rate, electroencephalogram or electrocardiogram. Measuring voice is easy and recent work has shown very promising results in classifying cognitive workload levels using the speech signal [4][5][6]. Successful design and implementation of such a method would provide a powerful tool to developers of cognitive infocommunications systems [7].…”
Section: Introductionmentioning
confidence: 99%
“…There is a growing body of work that supports the statement that cognitive workload affects the speech signal. For example, a data set of 15 participants was presented in [4] where each participant performed reading and Stroop tasks. The difficulty levels of these tasks were classified using mel-frequency cepstrum coefficients and prosodic features and a classifier based on a speaker-adapted Gaussian mixture model.…”
Section: Introductionmentioning
confidence: 99%