Emotion recognition (ER) from speech signals is a robust approach since it cannot be imitated like facial expression or text based sentiment analysis. Valuable information underlying the emotions are significant for human-computer interactions enabling intelligent machines to interact with sensitivity in the real world. Previous ER studies through speech signal processing have focused exclusively on associations between different signal mode decomposition methods and hidden informative features. However, improper decomposition parameter selections lead to informative signal component losses due to mode duplicating and mixing. In contrast, the current study proposes VGG-optiVMD, an empowered variational mode decomposition algorithm, to distinguish meaningful speech features and automatically select the number of decomposed modes and optimum balancing parameter for the data fidelity constraint by assessing their effects on the VGG16 flattening output layer. Various feature vectors were employed to train the VGG16 network on different databases and assess VGG-optiVMD reproducibility and reliability. One, two, and three-dimensional feature vectors were constructed by concatenating Mel-frequency cepstral coefficients, Chromagram, Mel spectrograms, Tonnetz diagrams, and spectral centroids. Results confirmed a synergistic relationship between the fine-tuning of the signal sample rate and decomposition parameters with classification accuracy, achieving state-of-the-art 96.09% accuracy in predicting seven emotions on the Berlin EMO-DB database.
In todays competitive landscape, businesses grapple with customer retention. Churn prediction models, although beneficial, often lack accuracy due to the reliance on a single data source. The intricate nature of human behavior and high dimensional customer data further complicate these efforts. To address these concerns, this paper proposes a multimodal fusion learning model for identifying customer churn risk levels in financial service providers. Our multimodal approach integrates customer sentiments financial literacy (FL) level, and financial behavioral data, enabling more accurate and bias-free churn prediction models. The proposed FL model utilizes a SMOGN COREG supervised model to gauge customer FL levels from their financial data. The baseline churn model applies an ensemble artificial neural network and oversampling techniques to predict churn propensity in high-dimensional financial data. We also incorporate a speech emotion recognition model employing a pre-trained CNN-VGG16 to recognize customer emotions based on pitch, energy, and tone. To integrate these diverse features while retaining unique insights, we introduced late and hybrid fusion techniques that complementary boost coordinated multimodal co learning. Robust metrics were utilized to evaluate the proposed multimodal fusion model and hence the approach validity, including mean average precision and macro-averaged F1 score. Our novel approach demonstrates a marked improvement in churn prediction, achieving a test accuracy of 91.2%, a Mean Average Precision (MAP) score of 66, and a Macro-Averaged F1 score of 54 through the proposed hybrid fusion learning technique compared with late fusion and baseline models. Furthermore, the analysis demonstrates a positive correlation between negative emotions, low FL scores, and high-risk customers.
Emotion recognition (ER) from speech signals is a robust approach since it cannot be imitated like facial expression or text based sentiment analysis. Valuable information underlying the emotions are significant for human-computer interactions enabling intelligent machines to interact with sensitivity in the real world. Previous ER studies through speech signal processing have focused exclusively on associations between different signal mode decomposition methods and hidden informative features. However, improper decomposition parameter selections lead to informative signal component losses due to mode duplicating and mixing. In contrast, the current study proposes VGG-optiVMD, an empowered variational mode decomposition algorithm, to distinguish meaningful speech features and automatically select the number of decomposed modes and optimum balancing parameter for the data fidelity constraint by assessing their effects on the VGG16 flattening output layer. Various feature vectors were employed to train the VGG16 network on different databases and assess VGG-optiVMD reproducibility and reliability. One, two, and three-dimensional feature vectors were constructed by concatenating Mel-frequency cepstral coefficients, Chromagram, Mel spectrograms, Tonnetz diagrams, and spectral centroids. Results confirmed a synergistic relationship between the fine-tuning of the signal sample rate and decomposition parameters with classification accuracy, achieving state-of-the-art 96.09% accuracy in predicting seven emotions on the Berlin EMO-DB database.
The accurate classification of human emotions from speech remains a formidable challenge due to the dynamic, non-stationary properties of audio signals and pervasive background noise. Traditional single-domain extraction methods frequently fail to capture overlapping acoustic phenomena, resulting in high misclassification rates among acoustically similar emotions. To overcome this, we propose the Dual-Decomposition Ensemble (DDE-SER), an architecture that synergizes 1D adaptive frequency filtering with 2D spatial spectrogram separation. The framework operates through two distinct pipelines: an adaptive time-domain branch that leverages VGG-optiVMD to autonomously extract Intrinsic Mode Functions (IMFs), and a structural spectrogram branch that applies orthogonal median filtering to decouple continuous harmonic formants from transient percussive noises. The primary novel contribution is a trainable Gated Attention mechanism that dynamically fuses these two previously established orthogonal decomposition pipelines based on the underlying emotional context, mitigating feature redundancy without the parameter overhead of large foundation models. Additionally, an acoustic perturbation strategy involving targeted pitch shifts and noise injection is applied to prevent overfitting on pristine studio datasets. Validated using a rigorous Speaker-Independent Cross-Validation (SICV) methodology, DDE-SER demonstrates competitive predictive performance, achieving an overall accuracy of 85.30% on the EMO-DB corpus and 62.17% on the seven-class RAVDESS corpus. Diagnostic results confirm the framework partially mitigates ambiguities between high-arousal states, such as Anger and Happiness, while maintaining the lightweight computational efficiency required for affective computing deployments.