Machine learning techniques for speech emotion recognition using paralinguistic acoustic features

Jha, Tulika; Kavya, R; Christopher, Jabez; Arunachalam, Vasan

doi:10.1007/s10772-022-09985-6

Cited by 12 publications

(3 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(2) Resonance peaks The fact that people can still recognise and understand sounds in noisy environments is closely related to the resonance peak feature that carries the discriminative properties of the sound, in addition to the robustness of humans to noise [15][16]. Treating the vocal tract as a resonant cavity for articulation, the vocal tract will oscillate back and forth to its maximum amplitude when the excitation frequency is equal to the resonant frequency of the vocal tract, i.e.…”

Section: Speech Emotion Feature Extractionmentioning

confidence: 99%

Speech Emotion Recognition Based on Fuzzy Support Vector Machine

2022

View full text Add to dashboard Cite

Language is an important part of everyday information communication, and automatic speech emotion information recognition technology has broad application prospects in education, services and medicine. The purpose of this paper is to study speech emotion recognition by specific fuzzy support vector machines. The applicability of fuzzy theory for solving speech emotion states is investigated and the theory of support vector machines, fuzzy support vector machines, is introduced to analyse speech emotion feature extraction in terms of both short-time energy and resonance peaks. The performance of SVM and FSVM methods are compared using Emo-DB corpus tests and it is found that the FSVM method has a higher recognition rate than the SVM method.

show abstract

Section: Speech Emotion Feature Extractionmentioning

confidence: 99%

Speech Emotion Recognition Based on Fuzzy Support Vector Machine

2022

View full text Add to dashboard Cite

show abstract

“…The SER task involves two basic processing steps: speech feature extraction [ 4 ], which transforms the original speech signal into lower-dimensional latent features, and speech emotion classification [ 5 ], which uses the extracted latent features to satisfy task requirements. In recent years, speech feature extraction technologies have been affected by the boom in computer vision (CV) and natural language processing (NLP) fields, often drawing on some current methods for extracting image spatial features or text temporal features.…”

Section: Introductionmentioning

confidence: 99%

ACG-EmoCluster: A Novel Framework to Capture Spatial and Temporal Information from Emotional Speech Enhanced by DeepCluster

Zhao

Zha

et al. 2023

Sensors

View full text Add to dashboard Cite

Speech emotion recognition (SER) is a task that tailors a matching function between the speech features and the emotion labels. Speech data have higher information saturation than images and stronger temporal coherence than text. This makes entirely and effectively learning speech features challenging when using feature extractors designed for images or texts. In this paper, we propose a novel semi-supervised framework for extracting spatial and temporal features from speech, called the ACG-EmoCluster. This framework is equipped with a feature extractor for simultaneously extracting the spatial and temporal features, as well as a clustering classifier for enhancing the speech representations through unsupervised learning. Specifically, the feature extractor combines an Attn–Convolution neural network and a Bidirectional Gated Recurrent Unit (BiGRU). The Attn–Convolution network enjoys a global spatial receptive field and can be generalized to the convolution block of any neural networks according to the data scale. The BiGRU is conducive to learning temporal information on a small-scale dataset, thereby alleviating data dependence. The experimental results on the MSP-Podcast demonstrate that our ACG-EmoCluster can capture effective speech representation and outperform all baselines in both supervised and semi-supervised SER tasks.

show abstract

“…In conclusion, underwater wireless communication and image processing are important elds of research that have been gaining increasing attention in recent years (Jha et al 2022;Rahmeni et al 2022). The unique challenges of the underwater environment, such as slow propagation, limited bandwidth, and high attenuation, require specialized techniques for communication and image processing.…”

Section: Introductionmentioning

confidence: 99%

A Novel Method for Classification and Modelling of Underwater Acoustic Communication through Machine Learning and Image Processing Technique

Shaik,

Das

2023

Preprint

View full text Add to dashboard Cite

The increasing prevalence of underwater activities has highlighted the urgent need for reliable underwater acoustic communication systems. However, the challenging nature of the underwater environment poses significant obstacles to the implementation of conventional voice communication methods. To better understand and improve upon these systems, simulations of the underwater audio channel have been developed using mathematical models and assumptions. In this study, we utilize real-world informationgathered from both a measured water reservoir and Lake to evaluate the ability of machine learning and machine learning methods, specifically Long Short-Term Memory (LSTM) and Deep Neural Network (DNN), to accurately reconstruct the underwater audio channel. The outcomesvalidate the efficiency of machine learning methods, particularly LSTM, in accurately simulating the underwater acoustic communication channel with low mean absolute percentage error. Additionally, this research also includes an image processing to identify the objects present thein theacoustic environment.

show abstract

Machine learning techniques for speech emotion recognition using paralinguistic acoustic features

Cited by 12 publications

References 32 publications

Speech Emotion Recognition Based on Fuzzy Support Vector Machine

Speech Emotion Recognition Based on Fuzzy Support Vector Machine

ACG-EmoCluster: A Novel Framework to Capture Spatial and Temporal Information from Emotional Speech Enhanced by DeepCluster

A Novel Method for Classification and Modelling of Underwater Acoustic Communication through Machine Learning and Image Processing Technique

Contact Info

Product

Resources

About