Recognition of Emotions in German Speech Using Gaussian Mixture Models

Vondra, Martin; Vích, Robert

doi:10.1007/978-3-642-00525-1_26

Cited by 15 publications

(8 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is not entirely consistent with the results obtained from other authors using the EMO-DB database for GMM emotion recognition [37][38][39] as well as those published in more complex comparison studies [40,41]. Usually, the best recognized emotions are anger and sadness followed by neutral state, the emotion joy generates the most confusion being recognized as anger [39]. Similar results were also achieved in classifications accomplished in [33], where the same emotional speech database was used.…”

Section: Discussion Of Resultssupporting

confidence: 82%

Evaluation of influence of spectral and prosodic features on GMM classification of Czech and Slovak emotional speech

Přibil

Přibilová²

2013

J AUDIO SPEECH MUSIC PROC.

View full text Add to dashboard Cite

This article analyzes and compares influence of different types of spectral and prosodic features for Czech and Slovak emotional speech classification based on Gaussian mixture models (GMM). Influence of initial setting of parameters (number of mixture components and used number of iterations) for GMM training process was analyzed, too. Subsequently, analysis was performed to find how correctness of emotion classification depends on the number and the order of the parameters in the input feature vector and on the computation complexity. Another test was carried out to verify the functionality of the proposed two-level architecture comprising the gender recognizer and of the emotional speech classifier. Next tests were realized to find dependence of some negative aspect (processing of the input speech signal with too short time duration, the gender of a speaker incorrectly determined, etc.) on the stability of the results generated during the GMM classification process. Evaluations and tests were realized with the speech material in the form of sentences of male and female speakers expressing four emotional states (joy, sadness, anger, and a neutral state) in Czech and Slovak languages. In addition, a comparative experiment using the speech data corpus in other language (German) was performed. The mean classification error rate of the whole classifier structure achieves about 21% for all four emotions and both genders, and the best obtained error rate was 3.5% for the sadness style of the female gender. These values are acceptable in this first stage of development of the GMM classifier. On the other hand, the test showed the principal importance of correct classification of the speaker gender in the first level, which has heavy influence on the resulting recognition score of the emotion classification. This GMM classifier should be used for evaluation of the synthetic speech quality after applied voice conversion and emotional speech style transformation.

show abstract

Section: Discussion Of Resultssupporting

confidence: 82%

Evaluation of influence of spectral and prosodic features on GMM classification of Czech and Slovak emotional speech

Přibil

Přibilová²

2013

J AUDIO SPEECH MUSIC PROC.

View full text Add to dashboard Cite

show abstract

“…The most commonly used spectral features for emotion recognition are Mel-Frequency Cepstral Coefficients (MFCC) [35, 16, 15, 22, 29, 19, 11, 37, 8, 30, 21, 27, 14, 12, 32, 33, 36, 38, 39]. As in automatic speech recognition, MFCC are extracted using a 25 ms Hamming window at intervals of 10 ms and cover frequency range from 300 Hz to the Nyquist frequency.…”

Section: Prior Workmentioning

confidence: 99%

“…A real-time systems for discriminating between angry and neutral speech was implemented in [14] using GMMs for MFCC features in combination with a prosody-based classifier. Vondra and Vich [38] applied GMMs to emotion recognition using a combined feature set obtained by concatenating MFCC and prosodic features. Hu et al [12] employed the GMM supervector approach in order to extract fixed length feature vectors from utterances with variable durations.…”

Section: Prior Workmentioning

confidence: 99%

Class-level spectral features for emotion recognition

Bitouk

Verma

Nenkova

2010

Speech Communication

193

View full text Add to dashboard Cite

The most common approaches to automatic emotion recognition rely on utterance level prosodic features. Recent studies have shown that utterance level statistics of segmental spectral features also contain rich information about expressivity and emotion. In our work we introduce a more fine-grained yet robust set of spectral features: statistics of Mel-Frequency Cepstral Coefficients computed over three phoneme type classes of interest—stressed vowels, unstressed vowels and consonants in the utterance. We investigate performance of our features in the task of speaker-independent emotion recognition using two publicly available datasets. Our experimental results clearly indicate that indeed both the richer set of spectral features and the differentiation between phoneme type classes are beneficial for the task. Classification accuracies are consistently higher for our features compared to prosodic or utterance-level spectral features. Combination of our phoneme class features with prosodic features leads to even further improvement. Given the large number of class-level spectral features, we expected feature selection will improve results even further, but none of several selection methods led to clear gains. Further analyses reveal that spectral features computed from consonant regions of the utterance contain more information about emotion than either stressed or unstressed vowel features. We also explore how emotion recognition accuracy depends on utterance length. We show that, while there is no significant dependence for utterance-level prosodic features, accuracy of emotion recognition using class-level spectral features increases with the utterance length.

show abstract

“…A variety of pattern recognition methods have been explored for automatic emotion recognition such as gaussian mixture models (Luengo et al, 2005; Vlasenko et al, 2007; Vondra and Vich, 2009), hidden Markov models (Nwe et al, 2003; Shafran et al, 2003; Meng et al, 2007), neural network (Nicholson et al, 2000) and support vector machines (Kwon et al, 2003; Tabatabaei et al, 2007; Bitouk et al, 2010; Lee et al, 2011), regression (Grimm et al, 2007b). All of these seemingly diverse methods are designed to predict the emotion of a single test utterance in isolation.…”

Section: Introductionmentioning

confidence: 99%

Speaker-sensitive emotion recognition via ranking: Studies on acted and spontaneous speech

Cao

Verma

Nenkova

2015

Computer Speech & Language

102

View full text Add to dashboard Cite

We introduce a ranking approach for emotion recognition which naturally incorporates information about the general expressivity of speakers. We demonstrate that our approach leads to substantial gains in accuracy compared to conventional approaches. We train ranking SVMs for individual emotions, treating the data from each speaker as a separate query, and combine the predictions from all rankers to perform multi-class prediction. The ranking method provides two natural benefits. It captures speaker specific information even in speaker-independent training/testing conditions. It also incorporates the intuition that each utterance can express a mix of possible emotion and that considering the degree to which each emotion is expressed can be productively exploited to identify the dominant emotion. We compare the performance of the rankers and their combination to standard SVM classification approaches on two publicly available datasets of acted emotional speech, Berlin and LDC, as well as on spontaneous emotional data from the FAU Aibo dataset. On acted data, ranking approaches exhibit significantly better performance compared to SVM classification both in distinguishing a specific emotion from all others and in multi-class prediction. On the spontaneous data, which contains mostly neutral utterances with a relatively small portion of less intense emotional utterances, ranking-based classifiers again achieve much higher precision in identifying emotional utterances than conventional SVM classifiers. In addition, we discuss the complementarity of conventional SVM and ranking-based classifiers. On all three datasets we find dramatically higher accuracy for the test items on whose prediction the two methods agree compared to the accuracy of individual methods. Furthermore on the spontaneous data the ranking and standard classification are complementary and we obtain marked improvement when we combine the two classifiers by late-stage fusion.

show abstract

Recognition of Emotions in German Speech Using Gaussian Mixture Models

Cited by 15 publications

References 5 publications

Evaluation of influence of spectral and prosodic features on GMM classification of Czech and Slovak emotional speech

Evaluation of influence of spectral and prosodic features on GMM classification of Czech and Slovak emotional speech

Class-level spectral features for emotion recognition

Speaker-sensitive emotion recognition via ranking: Studies on acted and spontaneous speech

Contact Info

Product

Resources

About