A Survey of Classification Techniques in Speech Emotion Recognition

Roy, Tapas; Marwala, Tshilidzi; Chakraverty, Snehashish

doi:10.1002/9781119585640.ch3

Cited by 11 publications

(5 citation statements)

References 85 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…, deep neural networks, is to employ transfer learning. Recently[ 109 ] has reviewed the application of generalizable transfer learning in AER in the existing literature. In particular, it provides an overview of the previously proposed transfer learning methods for speech-based emotion recognition by listing 21 relevant studies.…”

Section: The Data Science Approachmentioning

confidence: 99%

Emotion recognition support system: Where physicians and psychiatrists meet linguists and data engineers

Adibi¹,

Kalani²,

Jalal³

et al. 2023

World J Psychiatry

View full text Add to dashboard Cite

An important factor in the course of daily medical diagnosis and treatment is understanding patients’ emotional states by the caregiver physicians. However, patients usually avoid speaking out their emotions when expressing their somatic symptoms and complaints to their non-psychiatrist doctor. On the other hand, clinicians usually lack the required expertise (or time) and have a deficit in mining various verbal and non-verbal emotional signals of the patients. As a result, in many cases, there is an emotion recognition barrier between the clinician and the patients making all patients seem the same except for their different somatic symptoms. In particular, we aim to identify and combine three major disciplines (psychology, linguistics, and data science) approaches for detecting emotions from verbal communication and propose an integrated solution for emotion recognition support. Such a platform may give emotional guides and indices to the clinician based on verbal communication at the consultation time.

show abstract

Section: The Data Science Approachmentioning

confidence: 99%

Emotion recognition support system: Where physicians and psychiatrists meet linguists and data engineers

Adibi¹,

Kalani²,

Jalal³

et al. 2023

World J Psychiatry

View full text Add to dashboard Cite

show abstract

“…The performance rate of a classifier largely depends on the type of feature extraction acquired. 35 Many hand-crafted features have been discovered by researchers to aid prediction performances. These include prosodic features (i.e., pitch, energy, zero crossing rate), 36,37 spectral features such as mel-frequency cepstral coefficients (MFCC), 38,39 gammatone frequency cepstral coefficients (GFCC), 40,41 human factor cepstral coefficients (HFCC), 41 linear predictor coefficients (LPC) and linear predictor cepstral coefficients (LPCC), 42,43 Teager-energy-operator (TEO) based features like TEO-decomposed FM variation (TEO-FM-Var), normalized TEO autocorrelation envelope area (TEO-Auto-Env) and critical bandbased TEO autocorrelation envelope area (TEO-CB-Auto-Env), 44,45 and quality features such as voice quality, tense, breathy and harsh.…”

Section: Ser Featuresmentioning

confidence: 99%

“…An emotional recognition system with respect to speech comprises of extraction of features and the prediction of emotions out of the extracted features via classification method. The performance rate of a classifier largely depends on the type of feature extraction acquired 35 . Many hand‐crafted features have been discovered by researchers to aid prediction performances.…”

Section: Related Workmentioning

confidence: 99%

Cross lingual speech emotion recognition via triple attentive asymmetric convolutional neural network

et al. 2020

View full text Add to dashboard Cite

The application of cross-corpus for speech emotion recognition (SER) via domain adaptation methods have gain high acknowledgment for developing good robust emotion recognition systems using different corpora or datasets. However, the issue of crosslingual still remains a challenge in SER and needs more attention to resolve the scenario of applying different language types in both training and testing. In this paper, we propose a triple attentive asymmetric convolutional neural network to address the recognition of emotions for cross-lingual and crosscorpus speech in an unsupervised approach. The proposed method adopts the joint supervision of softmax loss and center loss to learn high power discriminative feature representations for target domain via the use of high quality pseudo-labels. The proposed model uses three attentive convolutional neural networks asymmetrically, where two of the networks are used to artificially label unlabeled target samples as a result of their predictions from training on source labeled samples and the other network is used to obtain salient target discriminative features from the pseudo-labeled target samples. We evaluate our proposed method on three different language types (i.e., English, German, and Italian) data sets. The experimental results indicate that, our proposed method achieves higher prediction accuracy over other state-of-the-art methods.

show abstract

“…The emotional features in speech signals can be extracted by the classification model. Speech emotional features are divided into three main categories: rhythmic features, phonological-related features, and spectral features [8]- [9].…”

Section: Introductionmentioning

confidence: 99%

Speech emotion recognition based on dynamic convolutional neural network

Lin¹,

Hu²,

Zhu³

2023

JCEIM

View full text Add to dashboard Cite

In speech emotion recognition, the use of deep learning algorithms that extract and classify features of audio emotion samples usually requires the use of a large amount of resources, which makes the system more complex. This paper proposes a speech emotion recognition system based on dynamic convolutional neural network combined with bi-directional long and short-term memory network. On the one hand, the dynamic convolutional kernel allows the neural network to extract global dynamic emotion information, which can improve the performance while ensuring the computational power of the model, and on the other hand, the bi-directional long and short-term memory network enables the model to classify the emotion features more effectively with the temporal information. In this paper, we use CISIA Chinese speech emotion dataset, EMO-DB German emotion corpus and IEMOCAP English corpus to conduct experiments, and the average emotion recognition accuracy of the experimental results are 59.08%, 89.29% and 71.25%, which are 1.17%, 1.36% and 2.97% higher than the accuracy of speech emotion recognition systems using mainstream models, respectively. The effectiveness of the method in this paper is proved.

show abstract

A Survey of Classification Techniques in Speech Emotion Recognition

Cited by 11 publications

References 85 publications

Emotion recognition support system: Where physicians and psychiatrists meet linguists and data engineers

Emotion recognition support system: Where physicians and psychiatrists meet linguists and data engineers

Cross lingual speech emotion recognition via triple attentive asymmetric convolutional neural network

Speech emotion recognition based on dynamic convolutional neural network

Contact Info

Product

Resources

About