We provide a novel perspective on conversational emotion recognition by drawing an analogy between the task and a complete span of quantum measurement. We characterize different steps of quantum measurement in the process of recognizing speakers' emotions in conversation, and stitch them up with a quantum-like neural network. The quantum-like layers are implemented by complex-valued operations to ensure an authentic adoption of quantum concepts, which naturally enables conversational context modeling and multimodal fusion. We borrow an existing algorithm to learn the complex-valued network weights, so that the quantum-like procedure is conducted in a data-driven manner. Our model is comparable to state-of-the-art approaches on two benchmarking datasets, and provide a quantum view to understand conversational emotion recognition.
We provide a novel perspective on conversational emotion recognition by drawing an analogy between the task and a complete span of quantum measurement. We characterize different steps of quantum measurement in the process of recognizing speakers' emotions in conversation, and stitch them up with a quantum-like neural network. The quantum-like layers are implemented by complex-valued operations to ensure an authentic adoption of quantum concepts, which naturally enables conversational context modeling and multimodal fusion. We borrow an existing algorithm to learn the complex-valued network weights, so that the quantum-like procedure is conducted in a data-driven manner. Our model is comparable to state-of-the-art approaches on two benchmarking datasets, and provide a quantum view to understand conversational emotion recognition.
Abstract This study explores Quantum AI’s potential in enhancing Speech Emotion Recognition (SER) systems. Our primary objective is to evaluate the performance of quantum-inspired algorithms compared to classical machine-learning approaches in accurately identifying and classifying emotions from speech signals. We hypothesise that quantum computing techniques can improve the efficiency and accuracy of emotion recognition, particularly in handling complex, highdimensional acoustic data. We developed a hybrid quantum-classical model that combines quantum-inspired neural networks with traditional feature extraction techniques. Our approach utilises quantum circuits for data encoding and quantum variational algorithms for classification. We implemented quantum versions of support vector machines (QSVM) and quantum approximate optimisation algorithms (QAOA) for emotion classification tasks. These quantum methods were compared against a hybrid Convolutional Neural Network and Long Short Term (LSTM). The hybrid network is called a Convolutional Long Short Term network(CLSTM). The study employed a custom dataset for speech emotion recognition. We prepossessed the audio data to extract relevant acoustic features, including mel-frequency cepstral coefficients (MFCCs), pitch, and energy. In contrast, our implemented quantum-inspired model for this corpus showed lower performance, with the highest training accuracy of 30%, struggling with most emotions but performing best with ’Trust’. These varied results across different implementations suggest that while Quantum AI techniques show promise in advancing speech emotion recognition, their effectiveness may depend on the specific dataset, language, and model architecture used. Finally, the speed of a simulated quantum network is shown to outperform current methods in terms of matrix multiplication by leaps and bounds.
Quantum computing has emerged as a breakthrough technology for sentiment and emotion analysis, providing computational efficiency and interpretability benefits. This paper compares three quantum-inspired methods: fully complex-valued neural networks, multimodal sentiment analysis models, and quantum affective computing. This paper compares three quantum-inspired methods: fully complex-valued neural networks, multimodal sentiment analysis models, and quantum affective computing models. The research uses six benchmark sentiment datasets (CR, MPQA, MR, SST-2, SUBJ, and SST-5) to compare the performance of the methods. The approach involves representing textual and multimodal data as complex quantum states, using quantum-inspired feature representations, and using quantum measurement methods for classification. The results show that the Complex Quantum Neural Network (QNN) performs better than baseline models such as BERT and RoBERTa, with the best F1-scores on all datasets. Specifically, it has an F1-score of 86 on CR, 86 on MPQA, 90 on MR, 88 on SST-2, 97 on SUBJ, and 53 on SST-5, outperforming baseline deep learning methods. These results show the potential of quantum computing to revolutionize sentiment analysis, providing more efficient and interpretable models with better contextual understanding and scalability.
This paper presents SentiQNN (Sentiment Quantum Neural Network), a novel quantum-inspired neural network architecture specifically designed for sentiment analysis tasks in natural language processing. SentiQNN leverages quantum computing principles including superposition, entanglement, and quantum measurement to enhance traditional neural network capabilities for text classification. The model incorporates complex-valued embeddings, quantum mixture operations, and multi-task learning with sentiment lexicon integration to achieve superior performance in sentiment classification tasks. Through extensive experimentation across multiple benchmark datasets, SentiQNN demonstrates state-of-the-art performance with 88.11% accuracy, outperforming traditional classical approaches by 3-7%. The architecture introduces innovative quantum state preparation layers, quantum circuit operations, and quantum measurement mechanisms specifically optimized for natural language understanding. Our comprehensive evaluation reveals that quantum-inspired approaches can significantly enhance sentiment analysis performance while maintaining computational efficiency. The findings contribute to the emerging field of quantum machine learning and provide a foundation for future research in quantum-enhanced natural language processing systems.
A long-standing goal in the field of Artificial Intelligence (AI) is to develop systems that can perceive and understand human multimodal language. This requires both the consideration of context in the form of surrounding utterances in a conversation, i.e., context modelling, as well as the impact of different modalities (e.g., linguistic, visual acoustic), i.e., multimodal fusion. In the last few years, significant strides have been made towards the interpretation of human language due to simultaneous advancement in deep learning, data gathering and computing infrastructure. AI models have been investigated to either model interactions across distinct modalities, i.e., linguistic, visual and acoustic, or model interactions across parties in a conversation, achieving unprecedented levels of performance. However, AI models are often designed with only performance as their design target, leaving aside other essential factors such as transparency, interpretability, and how humans understand and reason about cognitive states. In line with this observation, in this dissertation, we develop quantum probabilistic neural models and techniques that allow us to capture rational and irrational cognitive biases, without requiring a priori understanding and identification of them. First, we present a comprehensive empirical comparison of state-of-the-art (SOTA) modality fusion strategies for video sentiment analysis. The findings provide us helpful insights into the development of more effective modality fusion models incorporating quantum-inspired components. Second, we introduce an end-to-end complex-valued neural model for video sentiment analysis, simulating quantum procedural steps, outside of physics, into the neural network modelling paradigm. Third, we investigate non-classical correlations across different modalities. In particular, we describe a methodology to model interactions between image and text for an information retrieval scenario. The results provide us with theoretical and empirical insights to develop a transparent end-to-end probabilistic neural model for video emotion detection in conversations, capturing non-classical correlations across distinct modalities. Fourth, we introduce a theoretical framework to model user's cognitive states underlying their multimodal decision perspectives, and propose a methodology to capture interference of modalities in decision making. Overall, we show that our models advance the SOTA on various affective analysis tasks, achieve high transparency due to the mapping to quantum physics meanings, and improve post-hoc interpretability, unearthing useful and explainable knowledge about cross-modal interactions.
Emotional cognition is nonlinear, probabilistic, and interdependent, making it hard to recreate human emotional intelligence in AI systems. The study offers the Quantum-Emotion Neural Network (QENN). This unique Quantum Physics-Inspired AI approach uses aspects of quantum mechanics such as superposition, entanglement, and quantum probability amplitudes in neural network design. Where regular models handle emotions as non-interacting or unchanging parts, QENN represents them using amplitude encoding and quantum-inspired neurons to allow all emotional states to be managed together. Training and evaluation of the model took place on the IndiComics Emotion (ICE) dataset, which has 17,340 multimodal instances over eight emotion classes-happy, Sad, Angry, Fearful, Disgust, Surprised, Neutral, and Mixed emotions. The tests showed QENN achieved better results than CNN and LSTM, with an accuracy of 93.8%, 93.5% precision, 92.9% recall, an F1-score of 93.2%, and an ROC-AUC of 95.8% overall. In contrast, traditional CNN and LSTM models had 84.7% and 85.3% accuracies, and their ROC-AUC was 87.2% and 88.5%, respectively. Evaluation with the confusion matrix showed that precision remained above 90% in all emotion types, even for complex ones like ‘Mixed.’ Also, the training-validation accuracy curves revealed excellent generalisation and limited overfitting, with a learning rate of 0.001 giving the most minor validation loss, equal to 0.21. These outcomes show that quantum-inspired solutions are robust and easy to understand for emotion modelling. This work proves that QENN is a critical step forward in making machines that understand emotions as people do.
Emotion recognition seeks to identify a person’s state by examining signals such as facial expressions, speech, physiological signals and conversational content. Yet accurate emotion recognition presents obstacles because these signals can be complex, noisy, nonlinear and heavily affected by surrounding context. This paper investigates quantum-based representations combined with machine learning techniques to enhance emotion classification. The research examines emotion sources, including facial expressions, speech, EEG signals and conversational data. It explores how quantum-inspired techniques can merge with established deep learning methods to produce representations. The design presented fuses a neural network with a four qubit ZZFeatureMap component enabling the system to learn data from both conventional and quantum derived feature spaces. Experiments examined EEG segments for each participant and the system achieved average recognition rates of seventy nine point six percent for valence and eighty one point five percent for arousal across ten repeated trials. These findings show that quantum derived features can add information when combined with conventional deep learning methods. Nevertheless because experiments used simulated circuits the results do not prove a performance advantage over conventional techniques on actual quantum computers. The study also highlights difficulties such as quantum noise, computational scalability, experimental assessment, data privacy and real world deployment.