Voice source under cognitive load: Effects and classification

Yap, Tet Fei; Epps, Julien; Ambikairajah, Eliathamby; Choi, Eric H. C.

doi:10.1016/j.specom.2015.05.007

Cited by 33 publications

(26 citation statements)

References 56 publications

(92 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Cognitive Load with Speech and EGG (CLSE) dataset [13,10] was designed to support the investigation of acoustic features and evaluation of algorithms for the determination of a speaker's cognitive load and working memory during speech. The CLSE database comprises recordings of 20 male and 6 female native Australian English speakers.…”

Section: The Datasetmentioning

confidence: 99%

“…The "span" tasks are used to measure the working memory capacity of a subject [13], in which participants are required to remember concepts or objects in the presence of distractors [3,10]. The reading span task is based on the protocol described by Unsworth et Al.…”

Section: The Datasetmentioning

confidence: 99%

“…The reading span task is based on the protocol described by Unsworth et Al. [13,12]. It required the participants to read a series of (between two to five) possibly illogical short sentences, indicate whether the sentence read was true or false, and then remember a single letter presented briefly between sentences.…”

Section: The Datasetmentioning

confidence: 99%

See 2 more Smart Citations

Predicting Cognitive Load Levels from Speech Data

Luz

2016

Recent Advances in Nonlinear Speech Processing

View full text Add to dashboard Cite

Abstract. An analysis of acoustic features for a ternary cognitive load classification task and an application of a classification boosting method to the same task are presented. The analysis is based on a data set that encompasses a rich array of acoustic features as well as electroglottographic (EGG) data. Supervised and unsupervised methods for identifying constitutive features of the data set are investigated with the ultimate goal of improving prediction. Our experiments show that the different tasks used to elicit the speech for this challenge affect the acoustic features differently in terms of their predictive power and that different feature selection methods might be necessary across these sub-tasks. The sizes of the training sets are also an important factor, as evidenced by the fact that the use of boosting combined with feature selection was enough to bring the unweighted recall scores for the Stroop tasks well above a strong support vector machine baseline.

show abstract

Section: The Datasetmentioning

confidence: 99%

Section: The Datasetmentioning

confidence: 99%

See 1 more Smart Citation

Predicting Cognitive Load Levels from Speech Data

Luz

2016

Recent Advances in Nonlinear Speech Processing

View full text Add to dashboard Cite

show abstract

“…It is therefore essential to measure their cognitive load (CL) level and accordingly tailor the amount of workload assigning on them [1]. Among the methods have been proposed for CL level measurement, speech-based method has been recognized as an effective one due to the non-intrusive and inexpensive properties of speech signal [2][3].…”

Section: Introductionmentioning

confidence: 99%

“…In most of the previous studies in this research area, speech was recorded in laboratory environments where noise does not exist and hence speech is clean [2][3]. However, this is not the case for practical scenarios where speech is recorded at working environments e.g.…”

Section: Introductionmentioning

confidence: 99%

A study of effectiveness of speech enhancement for cognitive load classification in noisy conditions

Ambikairajah

Thiruvaran

et al. 2015

2015 International Conference on Advanced Technologies for Communications (ATC)

Self Cite

View full text Add to dashboard Cite

In the last decade, speech-features have been effectively utilized for estimating cognitive load level in ideal conditions where recorded speech is clean. However, in more realistic conditions, the recorded speech data is corrupted by noise. Hence, the employment of speech enhancement is essential to reduce the noise. In this paper, the effectiveness of three speech enhancement algorithms proposed in our previous studies are compared based on performance and processing time and the most suitable method is utilized to denoise the input noisy speech before feeding it to a cognitive load classification system in order to improve its performance. The results of this study indicate that the use of speech enhancement can reduce 3.0% of average relative error rate for the system under the effect of various noisy conditions.

show abstract

Task Load and Stress

Epps¹

2017

The Wiley Handbook of Human Computer Interaction

View full text Add to dashboard Cite

Voice source under cognitive load: Effects and classification

Cited by 33 publications

References 56 publications

Predicting Cognitive Load Levels from Speech Data

Predicting Cognitive Load Levels from Speech Data

A study of effectiveness of speech enhancement for cognitive load classification in noisy conditions

Task Load and Stress

Contact Info

Product

Resources

About