Speech Emotion Recognition via Sparse Learning-Based Fusion Model

Speech communication is a powerful tool for conveying intentions and emotions, fostering mutual understanding, and strengthening relationships. In the realm of natural human-computer interaction, speech-emotion recognition plays a crucial role. This process involves three stages: dataset collection,...

Full description

Saved in:
Bibliographic Details
Main Authors: Dong-Jin Min, Deok-Hwan Kim
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10767710/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846141948406005760
author Dong-Jin Min
Deok-Hwan Kim
author_facet Dong-Jin Min
Deok-Hwan Kim
author_sort Dong-Jin Min
collection DOAJ
description Speech communication is a powerful tool for conveying intentions and emotions, fostering mutual understanding, and strengthening relationships. In the realm of natural human-computer interaction, speech-emotion recognition plays a crucial role. This process involves three stages: dataset collection, feature extraction, and emotion classification. Collecting speech-emotion recognition datasets is a complex and costly process, leading to limited data volumes and uneven emotional distributions. This scarcity and imbalance pose significant challenges, affecting the accuracy and reliability of emotion recognition. To address these issues, this study introduces a novel model that is more robust and adaptive. We employ the Ranking Magnitude Method (RMM) based on sparse learning. We use the Root Mean Square (RMS) energy and Zero Crossing Rate (ZCR) as temporal features to measure the speech’s overall volume and noise intensity. The Mel Frequency Cepstral Coefficient (MFCC) is utilized to extract critical speech features, which are then integrated into a multivariate Long Short-Term Memory-Fully Convolutional Network (LSTM-FCN) model. We analyze the utterance levels using the log-Mel spectrogram for spatial features, processing these patterns through a 2D Convolutional Neural Network Squeeze and Excitation Network (CNN-SEN) model. The core of our method is a Sparse Learning-Based Fusion Model (SLBF), which addresses dataset imbalances by selectively retraining the underperforming nodes. This dynamic adjustment of learning priorities significantly enhances the robustness and accuracy of emotion recognition. Using this approach, our model outperforms state-of-the-art methods for various datasets, achieving impressive accuracy rates of 97.18%, 97.92%, 99.31%, and 96.89% for the EMOVO, RAVDESS, SAVE, and EMO-DB datasets, respectively.
format Article
id doaj-art-1375912aaa184dd38c7652ec93e6d3ff
institution Kabale University
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-1375912aaa184dd38c7652ec93e6d3ff2024-12-04T00:00:55ZengIEEEIEEE Access2169-35362024-01-011217721917723510.1109/ACCESS.2024.350656510767710Speech Emotion Recognition via Sparse Learning-Based Fusion ModelDong-Jin Min0https://orcid.org/0009-0007-4092-3132Deok-Hwan Kim1https://orcid.org/0000-0002-6048-9392Department of Electrical and Computer Engineering, Inha University, Incheon, South KoreaDepartment of Electrical and Computer Engineering, Inha University, Incheon, South KoreaSpeech communication is a powerful tool for conveying intentions and emotions, fostering mutual understanding, and strengthening relationships. In the realm of natural human-computer interaction, speech-emotion recognition plays a crucial role. This process involves three stages: dataset collection, feature extraction, and emotion classification. Collecting speech-emotion recognition datasets is a complex and costly process, leading to limited data volumes and uneven emotional distributions. This scarcity and imbalance pose significant challenges, affecting the accuracy and reliability of emotion recognition. To address these issues, this study introduces a novel model that is more robust and adaptive. We employ the Ranking Magnitude Method (RMM) based on sparse learning. We use the Root Mean Square (RMS) energy and Zero Crossing Rate (ZCR) as temporal features to measure the speech’s overall volume and noise intensity. The Mel Frequency Cepstral Coefficient (MFCC) is utilized to extract critical speech features, which are then integrated into a multivariate Long Short-Term Memory-Fully Convolutional Network (LSTM-FCN) model. We analyze the utterance levels using the log-Mel spectrogram for spatial features, processing these patterns through a 2D Convolutional Neural Network Squeeze and Excitation Network (CNN-SEN) model. The core of our method is a Sparse Learning-Based Fusion Model (SLBF), which addresses dataset imbalances by selectively retraining the underperforming nodes. This dynamic adjustment of learning priorities significantly enhances the robustness and accuracy of emotion recognition. Using this approach, our model outperforms state-of-the-art methods for various datasets, achieving impressive accuracy rates of 97.18%, 97.92%, 99.31%, and 96.89% for the EMOVO, RAVDESS, SAVE, and EMO-DB datasets, respectively.https://ieeexplore.ieee.org/document/10767710/Emotion recognition2D convolutional neural network squeeze and excitation networkmultivariate long short-term memory-fully convolutional networklate fusionsparse learning
spellingShingle Dong-Jin Min
Deok-Hwan Kim
Speech Emotion Recognition via Sparse Learning-Based Fusion Model
IEEE Access
Emotion recognition
2D convolutional neural network squeeze and excitation network
multivariate long short-term memory-fully convolutional network
late fusion
sparse learning
title Speech Emotion Recognition via Sparse Learning-Based Fusion Model
title_full Speech Emotion Recognition via Sparse Learning-Based Fusion Model
title_fullStr Speech Emotion Recognition via Sparse Learning-Based Fusion Model
title_full_unstemmed Speech Emotion Recognition via Sparse Learning-Based Fusion Model
title_short Speech Emotion Recognition via Sparse Learning-Based Fusion Model
title_sort speech emotion recognition via sparse learning based fusion model
topic Emotion recognition
2D convolutional neural network squeeze and excitation network
multivariate long short-term memory-fully convolutional network
late fusion
sparse learning
url https://ieeexplore.ieee.org/document/10767710/
work_keys_str_mv AT dongjinmin speechemotionrecognitionviasparselearningbasedfusionmodel
AT deokhwankim speechemotionrecognitionviasparselearningbasedfusionmodel