Speech emotion recognition using hidden Markov models

Nwe, Tin Lay; Foo, Say Wei; Silva, Liyanage C. De

doi:10.1016/s0167-6393(03)00099-2

Cited by 775 publications

(333 citation statements)

References 20 publications

Supporting

Mentioning

326

Contrasting

Unclassified

Order By: Relevance

“…In general, speech shows an increased pitch variability or range and an increased intensity of effort when people are in a heightened aroused emotional state (Williams and Stevens, 1972;Scherer, 1982;Rothganger et al, 1998;Mowrer et al, 1987). In a paper by Nwe et al (2003), an overview of paralinguistic characteristics of more specific emotions is given. Thus, it is generally known that paralinguistic information plays a key role in emotion recognition in speech.…”

Section: Introductionmentioning

confidence: 99%

Automatic discrimination between laughter and speech

Truong¹,

Leeuwen²

2007

Speech Communication

132

118

View full text Add to dashboard Cite

Emotions can be recognized by audible paralinguistic cues in speech. By detecting these paralinguistic cues that can consist of laughter, a trembling voice, coughs, changes in the intonation contour etc., information about the speaker's state and emotion can be revealed. This paper describes the development of a gender-independent laugh detector with the aim to enable automatic emotion recognition. Different types of features (spectral, prosodic) for laughter detection were investigated using different classification techniques (Gaussian Mixture Models, Support Vector Machines, Multi Layer Perceptron) often used in language and speaker recognition. Classification experiments were carried out with short pre-segmented speech and laughter segments extracted from the ICSI Meeting Recorder Corpus (with a mean duration of approximately 2 s). Equal error rates of around 3% were obtained when tested on speaker-independent speech data. We found that a fusion between classifiers based on Gaussian Mixture Models and classifiers based on Support Vector Machines increases discriminative power. We also found that a fusion between classifiers that use spectral features and classifiers that use prosodic information usually increases the performance for discrimination between laughter and speech. Our acoustic measurements showed differences between laughter and speech in mean pitch and in the ratio of the durations of unvoiced to voiced portions, which indicate that these prosodic features are indeed useful for discrimination between laughter and speech.

show abstract

Section: Introductionmentioning

confidence: 99%

Automatic discrimination between laughter and speech

Truong¹,

Leeuwen²

2007

Speech Communication

132

118

View full text Add to dashboard Cite

show abstract

“…Some studies focus on finding the most relevant acoustic features of emotions in speech as in (Nwe et al, 2003;Fernandez and Picard, 2005;Cichosz and Slot, 2005). Other studies search for the best machine learning algorithm to use in constructing the classifier as in (Oudeyer, 2003) or investigate different classifier architectures as in (Breazeal and Aryananda, 2002).…”

Section: Introductionmentioning

confidence: 99%

An evaluation of the robustness of existing supervised machine learning approaches to the classification of emotions in speech

Shami

Verhelst

2007

Speech Communication

111

View full text Add to dashboard Cite

In this study, the robustness of approaches to the automatic classification of emotions in speech is addressed. Among the many types of emotions that exist, two groups of emotions are considered, adult-to-adult acted vocal expressions of common types of emotions like happiness, sadness, and anger and adult-to-infant vocal expressions of affective intents also known as "motherese". Specifically, we estimate the generalization capability of two feature extraction approaches, the approach developed for Sony's robotic dog AIBO (AIBO) and the segment-based approach (SBA) of . Three machine learning approaches are considered, K-Nearest Neighbors (KNN), Support Vector Machines (SVM) and Adaboosted decision trees and four emotional speech databases are employed, Kismet, BabyEars, Danish, and Berlin databases.Single corpus experiments show that the considered feature extraction approaches AIBO and SBA are competitive on the four databases considered and that their performance is comparable with previously published results on the same databases. The best choice of machine learning algorithm seems to depend on the feature extraction approach considered.Multi corpus experiments are performed with the Kismet-BabyEars and the Danish-Berlin database pairs that contain parallel emotional classes. Automatic clustering of the emotional classes in the database pairs shows that the patterns behind the emotions in the Kismet-BabyEars pair are less database dependent than the patterns in the Danish-Berlin pair. In off-corpus testing the classifier is trained on one database of a pair and tested on the other. This provides little improvement over baseline classification. In integrated corpus testing, however, the classifier is machine learned on the merged databases and this gives promisingly robust classification results, which suggest that emotional corpora with parallel emotion classes recorded under different conditions can be used to construct a single classifier capable of distinguishing the emotions in the merged corpora. Such a classifier is more robust than a classifier learned on a single corpus as it can recognize more varied expressions of the same emotional classes. These findings suggest that the existing approaches for the classification of emotions in speech are efficient enough to handle larger amounts of training data without any reduction in classification accuracy.

show abstract

“…The approach of Nwe et al (2003) has several classes of emotions namely, the archetypal emotions of anger, disgust, fear, joy, sadness and surprise. They create a data base of 60 emotional utterances, which are used to train and the proposed system by using Hidden Markov Models.…”

Section: Related Workmentioning

confidence: 99%

“…They create a data base of 60 emotional utterances, which are used to train and the proposed system by using Hidden Markov Models. They compare the Low-FrequencyCoefficient (LFPC) features with feature of the Linear Prediction Cepstral Coefficients (LPCC) and Mel-Frequency Cepstral Coefficients (MFCC) features [10].…”

Section: Related Workmentioning

confidence: 99%

A Novel Real-Time Emotion Detection System for Advanced Driver Assistance Systems

Machot

Mosa

Fasih

et al. 2012

Autonomous Systems: Developments and Trends

View full text Add to dashboard Cite

This paper presents a real-time emotion recognition concept of voice streams. A comprehensive solution based on Bayesian Quadratic Discriminate Classifier(QDC) is developed. The developed system supports Advanced Driver Assistance Systems (ADAS) to detect the mood of the driver based on the fact that aggressive behavior on road leads to traffic accidents. We use only 12 features to classify between 5 different classes of emotions. We illustrate that the extracted emotion features are highly overlapped and how each emotion class is effecting the recognition ratio. Finally, we show that the Bayesian Quadratic Discriminate Classifier is an appropriate solution for emotion detection systems, where a real-time detection is deeply needed with a low number of features.

show abstract

Speech emotion recognition using hidden Markov models

Cited by 775 publications

References 20 publications

Automatic discrimination between laughter and speech

Automatic discrimination between laughter and speech

An evaluation of the robustness of existing supervised machine learning approaches to the classification of emotions in speech

A Novel Real-Time Emotion Detection System for Advanced Driver Assistance Systems

Contact Info

Product

Resources

About