Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Year Published

2012
2012
2013
2013

Publication Types

Select...
1
1

Relationship

0
2

Authors

Journals

citations
Cited by 4 publications
references
References 8 publications
0
2
0
Order By: Relevance
“…All these features can be combined in different ways-the problem being less the possibility to compute and combine them in brute force approaches, but finding out whether they really add new information and by that, help boosting performance in more general or cross-corpus and cross-task analyses, and help doing feature selection and reduction. An interesting alternative is to investigate expert-crafted higher-level features (Mubarak et al, 2006) such as perceptually motivated features (Wu et al, 2011;Mahdhaoui et al, 2010), or features based on pre-classification (Ringeval and Chetouani, 2008).…”
Section: Ten Recent and Future Trendsmentioning
confidence: 99%
“…All these features can be combined in different ways-the problem being less the possibility to compute and combine them in brute force approaches, but finding out whether they really add new information and by that, help boosting performance in more general or cross-corpus and cross-task analyses, and help doing feature selection and reduction. An interesting alternative is to investigate expert-crafted higher-level features (Mubarak et al, 2006) such as perceptually motivated features (Wu et al, 2011;Mahdhaoui et al, 2010), or features based on pre-classification (Ringeval and Chetouani, 2008).…”
Section: Ten Recent and Future Trendsmentioning
confidence: 99%
“…Thus, usage of spectral or cepstral features (Mel frequency cepstral coefficients, MFCCs) prevailed. In the meantime, a plethora of novel, mostly expert-crafted acoustic features, including perceptually motivated ones [49,78,99] or such that base on pre-classification [64] have been proposed and evaluated for paralinguistic analysis, along with the addition of more or less brute forced linguistic features (e. g., Bag of Words or Bag of N-grams). Furthermore, it has repeatedly been shown that enlarging the feature space can help boost accuracy [78,80].…”
Section: More and Novel Featuresmentioning
confidence: 99%