A Novel Approach for Classification of Speech Emotions Based on Deep and Acoustic Features

Er, Mehmet Bilal

doi:10.1109/access.2020.3043201

Cited by 76 publications

(37 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the future, more dynamic and biological systems can be developed by taking more practical conditions such as accurate drift velocity, vascular branching, the influence of blood molecules by developing a proposed mobile MC model. Also, estimation of the position of Tx and Rx in the environment can be considered to design a more dynamic model that has less signal to interference rate and high reception probability at the receiver using deep neural network (Niitsoo et al, 2018;Er, 2020;Wu and Tseng, 2021).…”

Section: Discussionmentioning

confidence: 99%

Comparison of the Mobile and Fixed Nano/Micro-Scale Systems by Using Monte Carlo Simulation for Different Viscosity Values

Işık

Işik

2021

Iğdır Üniversitesi Fen Bilimleri Enstitüsü Dergisi

View full text Add to dashboard Cite

Nano networks that are defined as a communication of nano-sized devices (Nano Machines) are a new nano/micro-scale system subject. In this study, on the contrary to the literature, a mobile nano network model has been used to analyze the proposed system in a different viscosity environment by using some Physics law. Because it is known that besides the molecules, which transport information between transmitter and receiver, the transmitter and receiver parts of the biological cells can be mobile in the blood or any other fluid media. In addition, the effect of viscosity which is an important part of the environment of the nano-device systems and distance between transmitter and receiver are analyzed detailed in Matlab with analytical and simulation results by comparing the fixed and mobile nano scale systems. It is concluded that when the receiver and transmitter are mobile, distance between them changes and finally this affects the probability of the received molecules at the receiver. As is expected, the fraction of received molecules is obtained the highest when the viscosity of the environment and distance are the lowest for both fixed and mobile system models. Also positions of receiver and transmitter show that when the distance of transmitter and receiver increases from the origin, fraction of received molecules decreases.

show abstract

Section: Discussionmentioning

confidence: 99%

Comparison of the Mobile and Fixed Nano/Micro-Scale Systems by Using Monte Carlo Simulation for Different Viscosity Values

Işık

Işik

2021

Iğdır Üniversitesi Fen Bilimleri Enstitüsü Dergisi

View full text Add to dashboard Cite

show abstract

“…It is the most widely used speech feature, which helps in characterising the properties from the voice signals [43].  Chroma -Related to energy density and give insight on the signal s harmonic content [44].  Mel Spectrogram -Instead of frequency domain, Mel Spectrograms envisage sounds on the Mel scale.…”

Section: Features Extracted For Punjabi Sermentioning

confidence: 99%

“… ZCR -It signifies the number of times that the zero point is crossed by the speech signals. It is also used as an evidence of frequency as well as noise [44].  Entropy -It signifies disorganization and can be used calculate the peakiness of a distribution [49].…”

Section: Features Extracted For Punjabi Sermentioning

confidence: 99%

Impact of Feature Extraction and Feature Selection Algorithms on Punjabi Speech Emotion Recognition Using Convolutional Neural Network

Kaur

Singh

2022

ACM Trans. Asian Low-Resour. Lang. Inf. Process.

View full text Add to dashboard Cite

The challenge to refine the spontaneity and productivity of a machine and human coherence, speech emotion recognition has been an overriding area of research. The trustability and fulfillment of such emotion recognition are largely involved with the feature extraction and selection processes. An important role is played in exploring and distinguishing audio content during the feature extraction phase. Also, the features that have been extracted should be tough to a number of disturbances and reliable enough for an adequate classification system. This paper focuses on three main components of a Speech Emotion Recognition (SER) Process. The first one is the optimal feature extraction method for Punjabi SER system. The second one is the use of an appropriate feature selection method that desires to select effectual features from the ones extracted in the first step, and removes the redundant features, to improve the conduct of emotion recognition. The third one is the classification model that has been used further for emotion recognition. So, the scope of this paper is to explain the three main steps of Punjabi SER system, feature extraction, feature selection, and emotion recognition with classifier. The results have been calculated and compared for number of feature set combinations, with and without feature selection process. A total of 10 experiments are carried out and various performance metrics such as precision, recall, F1-score, accuracy, etc. are used to demonstrate the results.

show abstract

“…Makine öğrenme teknikleri ve önceden belirlenmiş duygu etiketleri kullanılarak öznitelikleri çıkarılmış konuşma duyguları sınıflandırılabilmektedir. İnsanbilgisayar etkileşimi sonucunda konuşmadan duygu tanıma probleminde sınıflandırma doğruluğunu arttırmak için yeni bir hibrit mimari önermişlerdir (Er, 2020). Önerilen tekniğin konuşma duygularının doğru ve verimli bir şekilde sınıflandırılabilindiğini yapılan deneyler ile açık bir şekilde göstermişlerdir.…”

Section: Literatürtaramasıunclassified

Duygu Analizi İçin Yeni Bir Sözlük; NAYALex Duygu Sözlüğü

ATLI¹,

Ilhan²

2021

European Journal of Science and Technology

View full text Add to dashboard Cite

Özİletişimin ayrılmaz parçası olan duygular, farklı şekillerde (konuşma, jestler, yüz ifadeleri vb.) ortaya çıkmaktadır. Sosyal paylaşım platformlarında ise insanlar duygu ve düşüncelerini en çok metinsel paylaşımlar ile ifade etmektedir. İnsanların sosyal medya aracılığı ile paylaştığı metinler kişilerin duygu durumları hakkında fikir vermektedir. Kişilik tespitinde duyguların sıklığının kişilik özellikleri ile ilişkili olduğunu gösteren birçok çalışma yapılmıştır. Dolayısıyla, sosyal medyada paylaşılan mesajlarda saklı olan duyguların tespiti ve ortaya çıkarılması önemlidir. Metinlerde saklı olan duygular kelime-duygu sözlükleriyle ortaya çıkarılabilmektedir. Bu sözlüklere baktığımızda en fazla sayıda duygu çıkarımı yapabilen NRC Duygu Sözlüğü, olumlu-olumsuz ile birlikte 8 farklı duyguyu ortaya çıkarabilmektedir. Ancak metin aracılığı ile duygularını yansıtan kişilerin duygularını, olumlu-olumsuz veya birkaç farklı duygu ile sınırlı tutmak çoğu zaman kişilik tespitinde yetersiz kalmaktadır. Bu çalışmada, paylaşılan metinlerden daha fazla duygu yakalamak için metinden olumlu-olumsuz ile birlikte (umut, kaygı, sevgi, karamsarlık, iyimserlik, öfke, korku, üzüntü vb.) 38 farklı duygu çıkarımı yapan NAYALexsözlüğü önerilmektedir. NRC Duygu Sözlüğüne ve Plutchik'in Temel Duyguların Psikoevrimsel Teorisine dayandırdığımız sözlüğümüzün her bir kelimesi 38 farklı duygudan en az biri ile ilişkilendirilmiş 6469 İngilizce kelimeden oluşmaktadır. Instagram kullanıcı paylaşımlarına ait 10000 farklı paylaşımdan oluşan veri setimiz üzerinde birtakım deneyler yaparak, NAYALex sözlüğümüzün uygulanabilirliği ve kullanılabilirliği gösterilmiştir. Diğer (LIWC, EmoSenticNet, NRC, Empath) duygu sözlükleriyle karşılaştırıldığında, sözlüğümüz Tiffany'nin belirttiği 154 duygu için %24,7 ile en kapsamlı duyguyu tespit edebilir.

show abstract

A Novel Approach for Classification of Speech Emotions Based on Deep and Acoustic Features

Cited by 76 publications

References 44 publications

Comparison of the Mobile and Fixed Nano/Micro-Scale Systems by Using Monte Carlo Simulation for Different Viscosity Values

Comparison of the Mobile and Fixed Nano/Micro-Scale Systems by Using Monte Carlo Simulation for Different Viscosity Values

Impact of Feature Extraction and Feature Selection Algorithms on Punjabi Speech Emotion Recognition Using Convolutional Neural Network

Duygu Analizi İçin Yeni Bir Sözlük; NAYALex Duygu Sözlüğü

Contact Info

Product

Resources

About