Emotion recognition from speech: a review

Koolagudi, Shashidhar G.; Rao, K. Sreenivasa

doi:10.1007/s10772-011-9125-1

Cited by 486 publications

(207 citation statements)

References 75 publications

Supporting

Mentioning

177

Contrasting

Unclassified

Order By: Relevance

“…This finding is confirmed with what was found in [17], analysing read speech from the same Black Dog data set. Although formants are a widely used feature in the affect literature [25], their results were not good in either read or spontaneous speech in most of the speech part. However, the formants recognition rate using the "Sadness Characteristic" question, and using part of each sentence, performed better than other parts of speech.…”

Section: Resultsmentioning

confidence: 94%

Detecting depression: A comparison between spontaneous and read speech

Alghowinem

Goecke

Wagner

et al. 2013

2013 IEEE International Conference on Acoustics, Speech and Signal Processing

View full text Add to dashboard Cite

Major depressive disorders are mental disorders of high prevalence, leading to a high impact on individuals, their families, society and the economy. In order to assist clinicians to better diagnose depression, we investigate an objective diagnostic aid using affective sensing technology with a focus on acoustic features. In this paper, we hypothesise that (1) classifying the general characteristics of clinical depression using spontaneous speech will give better results than using read speech, (2) that there are some acoustic features that are robust and would give good classification results in both spontaneous and read, and (3) that a 'thin-slicing' approach using smaller parts of the speech data will perform similarly if not better than using the whole speech data. By examining and comparing recognition results for acoustic features on a real-world clinical dataset of 30 depressed and 30 control subjects using SVM for classification and a leave-one-out cross-validation scheme, we found that spontaneous speech has more variability, which increases the recognition rate of depression. We also found that jitter, shimmer, energy and loudness feature groups are robust in characterising both read and spontaneous depressive speech. Remarkably, thin-slicing the read speech, using either the beginning of each sentence or the first few sentences performs better than using all reading task data.

show abstract

Section: Resultsmentioning

confidence: 94%

Detecting depression: A comparison between spontaneous and read speech

Alghowinem

Goecke

Wagner

et al. 2013

2013 IEEE International Conference on Acoustics, Speech and Signal Processing

View full text Add to dashboard Cite

show abstract

“…To complicate matters further, the little work on automatic detection of depression from speech in the literature used different classifiers and different measures applied on different datasets, which make the comparison of results even harder; a general problem of most emotion recognition papers [12,13]. Therefore, there is a need for a comprehensive comparison of classifiers using the same dataset and measurements to identify the strongest feature (or group of features) and the most suitable classifier for depression detection.…”

Section: Related Workmentioning

confidence: 99%

A comparative study of different classifiers for detecting depression from spontaneous speech

Alghowinem

Goecke

Wagner

et al. 2013

2013 IEEE International Conference on Acoustics, Speech and Signal Processing

View full text Add to dashboard Cite

Accurate detection of depression from spontaneous speech could lead to an objective diagnostic aid to assist clinicians to better diagnose depression. Little thought has been given so far to which classifier performs best for this task. In this study, using a 60-subject real-world clinically validated dataset, we compare three popular classifiers from the affective computing literature -Gaussian Mixture Models (GMM), Support Vector Machines (SVM) and Multilayer Perceptron neural networks (MLP) -as well as the recently proposed Hierarchical Fuzzy Signature (HFS) classifier. Among these, a hybrid classifier using GMM models and SVM gave the best overall classification results. Comparing feature, score, and decision fusion, score fusion performed better for GMM, HFS and MLP, while decision fusion worked best for SVM (both for raw data and GMM models). Feature fusion performed worse than other fusion methods in this study. We found that loudness, root mean square, and intensity were the voice features that performed best to detect depression in this dataset.

show abstract

“…This database can be categorized as induced database [23] since captured sessions of SUS consist fabricated law suits situations in which non-professional actors take parts. Participants are supposed to act according to the storyline in each session, but a slight anticipation of controlled expression of emotional states may be expected.…”

Section: Emotional Databasementioning

confidence: 99%