Speech emotion recognition for SROL database using weighted KNN algorithm

Feraru, Monica; Zbancioc, Marius Dan

doi:10.1109/ecai.2013.6636198

Cited by 15 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each classifier has advantages and disadvantages in order to deal with the speech emotion recognition problem. The more common group used are composed of Hidden Markov Model (HMM) [34], [35] regarded as the simplest dynamic Bayesian networks, Gaussian Mixture Models (GMM) [36], Nearest-Neighbour classifiers [37], artificial neural networks (ANN) [38], support vector machine (SVM) [39], k-NN [40], Decision Trees [41] and many others. The vast majority of emotion recognition systems over speech have employed a highdimensional speech grouped in a big vector of features, so the main goal will be to handle the dimensionality in order to improve the emotion recognition performance.…”

Section: Introductionmentioning

confidence: 99%

Speech emotion recognition in emotional feedback for Human-Robot Interaction

Rázuri¹,

Sundgren²,

Rahmani³

et al. 2015

ijarai

View full text Add to dashboard Cite

Abstract-For robots to plan their actions autonomously and interact with people, recognizing human emotions is crucial. For most humans nonverbal cues such as pitch, loudness, spectrum, speech rate are efficient carriers of emotions. The features of the sound of a spoken voice probably contains crucial information on the emotional state of the speaker, within this framework, a machine might use such properties of sound to recognize emotions. This work evaluated six different kinds of classifiers to predict six basic universal emotions from non-verbal features of human speech. The classification techniques used information from six audio files extracted from the eNTERFACE05 audiovisual emotion database. The information gain from a decision tree was also used in order to choose the most significant speech features, from a set of acoustic features commonly extracted in emotion analysis. The classifiers were evaluated with the proposed features and the features selected by the decision tree. With this feature selection could be observed that each one of compared classifiers increased the global accuracy and the recall. The best performance was obtained with Support Vector Machine and bayesNet.

show abstract

Section: Introductionmentioning

confidence: 99%

Speech emotion recognition in emotional feedback for Human-Robot Interaction

Rázuri¹,

Sundgren²,

Rahmani³

et al. 2015

ijarai

View full text Add to dashboard Cite

show abstract

“…1) KNN-Based: KNN is a supervised learning algorithm, whose essence is to calculate the distance between different eigenvalues to classify samples [122]. The method of Feraru and Zbancioc [106] proposed an improved version of the KNN algorithm, which was associated with each parameter for SER according to the performance of feature vector weight in the classification processing. Rieger et al [107] utilized the integration of pattern recognition paradigm with spectral feature extraction (including CEP, MFCC, LSF, ACW, and PFL) and KNN classifiers to perform SER.…”

Section: B Trends In Speech Sentiment Analysismentioning

confidence: 99%

Sentiment Analysis: Comprehensive Reviews, Recent Advances, and Open Challenges

Sun

Long

et al. 2024

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

Sentiment analysis (SA) aims to understand the attitudes and views of opinion holders with computers. Previous studies have achieved significant breakthroughs and extensive applications in the past decade, such as public opinion analysis and intelligent voice service. With the rapid development of deep learning, SA based on various modalities has become a research hotspot. However, only individual modality has been analyzed separately, lacking a systematic carding of comprehensive SA methods. Meanwhile, few surveys covering the topic of multimodal SA (MSA) have been explored yet. In this article, we first take the modality as the thread to design a novel framework of SA tasks to provide researchers with a comprehensive understanding of relevant advances in SA. Then, we introduce the general workflows and recent advances of single-modal in detail, discuss the similarities and differences of single-modal SA in data processing and modeling to guide MSA, and summarize the commonly used datasets to provide guidance on data and methods for researchers according to different task types. Next, a new taxonomy is proposed to fill the research gaps in MSA, which is divided into multimodal representation learning and multimodal data fusion. The similarities and differences between these two methods and the latest advances are described in detail, such as dynamic interaction between multimodalities, and the multimodal fusion technologies are further expanded. Moreover, we explore the advanced studies on multimodal alignment, chatbots, and Chat Generative Pre-trained Transformer (ChatGPT) in SA. Finally, we discuss the open research challenges of MSA and provide four potential aspects to improve future works, such as cross-modal contrastive learning and multimodal pretraining models.

show abstract

“…are employed. The classifiers used for training and testing the system include k-nearest neighbors [4], Gaussian mixture model [5], support vector machines [6], and hidden Markov models [7], among others.…”

Section: Introductionmentioning

confidence: 99%

Multi-taper spectral features for emotion recognition from speech

Chapaneri

Jayaswal

2015

2015 International Conference on Industrial Instrumentation and Control (ICIC)

View full text Add to dashboard Cite

In this paper, the performance of mUlti-taper spectral estimate is investigated relative to conventional single taper estimate for the application of emotion recognition from speech signals. Typically, a single taper/window helps in reducing bias of the estimate, but due to its high variance, the resulting spectral features tend to give poor recognition performance. The weighted averages of the multi-tapered uncorrelated eigen spectra results in more discriminative spectral features, thus increasing the overall performance. We demonstrate that the application of six Multi-peak mUlti-tapers with support vector machine results in 81 % classification accuracy on seven emotions from Berlin emotion database considering only spectral features, compared to 72% using conventional Hamming window method.

show abstract

Speech emotion recognition for SROL database using weighted KNN algorithm

Cited by 15 publications

References 16 publications

Speech emotion recognition in emotional feedback for Human-Robot Interaction

Speech emotion recognition in emotional feedback for Human-Robot Interaction

Sentiment Analysis: Comprehensive Reviews, Recent Advances, and Open Challenges

Multi-taper spectral features for emotion recognition from speech

Contact Info

Product

Resources

About