Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

International Conference on Computer and Information Technology (ICCIT)

SALG-QCNN-SER: A Noise-Robust Quantum Convolutional Neural Network with Enhanced Cross-Domain Generalization for Speech Emotion Recognition

Md. Rifat Hossen, Md. Sarwar Hosain, Akif Mahdi, Tarun Debnath, M Alamgir Hossain

Published Dec 19, 2025• 0 citations
Publisher

Abstract

Emotion recognition in speech is essential for human-computer interaction. This study introduces a refined hybrid Quantum Convolutional Neural Network (QCNN) framework designed to substantially enhance Speech Emotion Recognition (SER). It addresses major challenges such as speaker variability, noise robustness, and cross-domain applicability that often limit classical deep learning models. By Utilizing quantum principles like superposition and entanglement within a 6-qubit, 8-layer parameterized circuit, the model derives highdimensional, noise-resistant features from speech signals. The method includes sophisticated preprocessing steps, such as bandpass filtering and energy-based Voice Activity Detection (VAD), followed by Mel-Frequency Cepstral Coefficients (MFCC) extraction. Evaluated on a diverse dataset of 4,515 samples across eight emotions (Angry, Calm, Disgust, Fear, Happy, Neutral, Sad, Surprised), the QCNN achieved an accuracy of 86 %, setting a new benchmark. It surpasses classical approaches such as a CNN with attention$(77 \%)$, a traditional QCNN$(77.87 \%)$, and a hybrid quantum-classical network$(76 \%)$. The model demonstrated balanced performance, with precision scores ranging from 0.79 to 1.0 (including a perfect 1.0 for Fear) and recall scores from 0.82 to 0.94. These results underscore the promise of quantum-enhanced neural networks in capturing complex, nonlinear speech emotion patterns and establishing a new standard for robust, generalizable SER systems.

DOI
10.1109/iccit68739.2025.11491179

Related papers

Classical to Quantum Neural Network Transfer Learning Approach for Speech Emotion Recognition

Sheikh Iftekhar Ahmed, Shaswata Mahernob Sarkar, Shaikh Anowarul Fattah +1 more

Speech emotion recognition (SER) has gained utmost attention among researchers for its vital role in Human-Computer Interaction, enabling systems to understand and respond to the emotional states of the users. In this work, the concept of transfer learning has been extended to the novel domain of hybrid classical-quantum neural networks for enhancing SER performance. The classical part involves preprocessing raw speech signals to generate three-channel log mel-spectrograms and the pretrained VGG 19 network for extracting useful emotional features. The quantum part is built upon a dressed quantum neural network (QNN), comprising multiple parallel QNN blocks, for accurate emotion classification. Extensive experiments on the publicly accessible TESS dataset reveal that the proposed hybrid transfer learning approach achieves state of the art accuracy of 98.93 %. An ablation study demonstrates the significant performance improvement attributed to the incorporation of QNN blocks. The integration of classical and quantum neural networks provides a robust and efficient solution, leveraging the strengths of both computational paradigms to enhance SER based applications.

IEEE Region 10 Conference (TENCON)•Dec 1, 2024•2 citations

HQTN-SER: Speech Emotion Recognition with Hybrid Quantum Tensor Networks

Mahad Mohtashim, Nouhaila Innan, Muhammad Shafique

Speech emotion recognition (SER) remains fragile in real-world conditions because emotional cues are subtle, speaker-dependent, and easily confounded by recording variability, while high-performing deep models typically rely on large and carefully curated training sets. Quantum machine learning offers an alternative way to introduce nonlinear correlation modeling with compact modules, yet existing quantum SER studies remain limited, and the impact of circuit structure is not well understood. This paper presents HQTN-SER, a hybrid quantum-classical framework that investigates how quantum tensor network connectivity can support SER under small-qubit settings. HQTN-SER introduces (i) an MPS-inspired quantum tensor network module that enforces structured interactions to model correlations in speech representations with a small number of trainable parameters, and (ii) a fusion strategy that combines quantum measurement features with a learned classical latent embedding for end-to-end emotion classification. We evaluate HQTN-SER on three public benchmarks (RAVDESS, SAVEE, and MDER) under a unified preprocessing and training protocol. The proposed model achieves test accuracies of 80.09\% on RAVDESS, 78.12\% on SAVEE, and 73.51\% on MDER, with corresponding macro-F1 scores of 0.8012, 0.7826, and 0.7351, respectively. The model also exhibits stable convergence while using only three or four qubits, suggesting that MPS-inspired circuit structure can be an effective and hardware-aware design choice for quantum-assisted SER. These results provide a compact experimental baseline for studying structured quantum modules in affective computing.

quant-pharXiv:2605.14523•May 15, 2026•0 citations

Representation learning with parameterised quantum circuits for advancing speech emotion recognition

Thejan Rajapakshe, Rajib Kumar Rana, Farina Riaz +2 more

Quantum machine learning (QML) offers a promising avenue for advancing representation learning in complex signal domains. In this study, we investigate the use of parameterised quantum circuits (PQCs) for speech emotion recognition (SER)-a challenging task due to the subtle temporal variations and overlapping affective states in vocal signals. We propose a hybrid quantum-classical architecture that integrates PQCs into a conventional convolutional neural network (CNN), leveraging quantum properties such as superposition and entanglement to enrich emotional feature representations. Experimental evaluations on three benchmark datasets IEMOCAP, RECOLA, and MSP-IMPROV-demonstrate that our hybrid model achieves improved classification performance relative to a purely classical CNN baseline, with over 50% reduction in trainable parameters. Furthermore, Adjusted Rand Index (ARI) analysis demonstrates that the quantum model yields feature representations with improved alignment to true emotion classes compared with the classical model, reinforcing the observed performance gains. This work provides early evidence of the potential for QML to enhance emotion recognition and lays the foundation for future quantum-enabled affective computing systems.

arXiv:2501.12050•Scientific Reports•Nov 22, 2025•7 citations

Hybrid Classical to Quantum Convolutional Neural Network With Enhanced Expressibility and Entanglement for Facial Emotion Recognition

Sheikh Iftekhar Ahmed, Shaswata Mahernob Sarkar, Shaikh Anowarul Fattah +1 more

Facial Emotion Recognition (FER) is essential for enhancing human-computer interaction and psychological analysis. Despite the progress in classical approaches, Quantum Convolutional Neural Networks (QCNNs) offer promising advancements by leveraging quantum parallelism and entanglement for more efficient feature processing. Combining the advantages of both classical and quantum domains, this study introduces a hybrid classical to enhanced QCNN (CEQCNN) framework for FER. The process begins with the pre-processing of facial images, followed by a supervised auto-encoder that leverages an additional classification loss, along with the reconstruction loss, to effectively extract discriminatively informative emotional features suitable for input to the QCNN. Traditional QCNN architectures suffer from a less expressive quantum feature space and insufficient post-pooling qubit correlation. The proposed enhanced QCNN architecture overcomes these limitations by introducing two new layers: the Expressible Convolutional Layer (Ex-Conv), which enhances quantum feature space representation utilizing a high expressibility ansatz, and the Entangled Convolutional Layer (En-Conv), which increases qubit entanglement after pooling to mitigate information loss. Extensive experimentation reveals that the supervised auto-encoder is effective for class-specific, organized feature extraction, and the combined integration of Ex-Conv and En-Conv layers within QCNN significantly improves the performance compared to traditional QCNN. Further analysis of expressibility and entangling capability justifies the effectiveness of these new layers. The proposed CEQCNN approach achieves 80.12% accuracy on FER-2013 and 91.98% on KDEF dataset, demonstrating a competitive position in the literature.

IEEE Transactions on Quantum Engineering•Jan 1, 2026•0 citations

Hybrid Quantum Machine Learning based Human Speech Emotion Recognition

Sparsh Mittal, Yash Chand, Mintu Kumar +1 more

This paper proposes hybrid quantum machine learning (QML) models for automatic emotion recognition from human speech signals. The proposed quantum support vector machine (QSVM) and hybrid quantum neural network (HQNN) models use Mel-Frequency Cepstral Coefficients (MFCC) as the features extracted from the speech data. We present a detailed analysis comparing the performance of QML models to conventional machine learning models for human speech-based emotion recognition, which is a multi-class classification problem. Our results illustrate that QSVM can achieve higher classification accuracy with a much reduced number of speech signal variables compared to traditional SVMs. Furthermore, the proposed HQNN classifier outperforms classical neural networks (NN) in terms of classification accuracy while utilizing a reduced number of training parameters. We have tested the performance of the HQNN model on a real IBM quantum computer. The results indicate that QML models provide a more effective and precise method for classification tasks involving the recognition of human emotions.

IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)•Apr 6, 2025•4 citations

Quantifying Quanvolutional Neural Networks Robustness for Speech in Healthcare Applications

Ha Tran, Bipasha Kashyap, Pubudu Nishantha Pathirana

Speech-based machine learning systems are sensitive to noise, complicating reliable deployment in emotion recognition and voice pathology detection. We evaluate the robustness of a hybrid quantum machine learning model, quanvolutional neural networks (QNNs) against classical convolutional neural networks (CNNs) under four acoustic corruptions (Gaussian noise, pitch shift, temporal shift, and speed variation) in a clean-train/corrupted-test regime. Using AVFAD (voice pathology) and TESS (speech emotion), we compare three QNN models (Random, Basic, Strongly) to a simple CNN baseline (CNN-Base), ResNet-18 and VGG-16 using accuracy and corruption metrics (CE, mCE, RCE, RmCE), and analyze architectural factors (circuit complexity or depth, convergence) alongside per-emotion robustness. QNNs generally outperform the CNN-Base under pitch shift, temporal shift, and speed variation (up to 22% lower CE/RCE at severe temporal shift), while the CNN-Base remains more resilient to Gaussian noise. Among quantum circuits, QNN-Basic achieves the best overall robustness on AVFAD, and QNN-Random performs strongest on TESS. Emotion-wise, fear is most robust (80-90% accuracy under severe corruptions), neutral can collapse under strong Gaussian noise (5.5% accuracy), and happy is most vulnerable to pitch, temporal, and speed distortions. QNNs also converge up to six times faster than the CNN-Base. To our knowledge, this is a systematic study of QNN robustness for speech under common non-adversarial acoustic corruptions, indicating that shallow entangling quantum front-ends can improve noise resilience while sensitivity to additive noise remains a challenge.

arXiv:2601.02432•Jan 5, 2026•0 citations
Emotion recognition in speech is essential for human-computer interaction. This study introduces a refined hybrid Quantum Convolutional Neural Network (QCNN) framework designed to substantially enhance Speech Emotion Recognition (SER). It addresses major challenges such as speaker variability, noise robustness, and cross-domain applicability that often limit classical deep learning models. By Utilizing quantum principles like superposition and entanglement within a 6-qubit, 8-layer parameterized circuit, the model derives highdimensional, noise-resistant features from speech signals. The method includes sophisticated preprocessing steps, such as bandpass filtering and energy-based Voice Activity Detection (VAD), followed by Mel-Frequency Cepstral Coefficients (MFCC) extraction. Evaluated on a diverse dataset of 4,515 samples across eight emotions (Angry, Calm, Disgust, Fear, Happy, Neutral, Sad, Surprised), the QCNN achieved an accuracy of 86 %, setting a new benchmark. It surpasses classical approaches such as a CNN with attention(77%)(77 \%)(77%), a traditional QCNN(77.87%)(77.87 \%)(77.87%), and a hybrid quantum-classical network(76%)(76 \%)(76%). The model demonstrated balanced performance, with precision scores ranging from 0.79 to 1.0 (including a perfect 1.0 for Fear) and recall scores from 0.82 to 0.94. These results underscore the promise of quantum-enhanced neural networks in capturing complex, nonlinear speech emotion patterns and establishing a new standard for robust, generalizable SER systems.
Speech emotion recognition (SER) has gained utmost attention among researchers for its vital role in Human-Computer Interaction, enabling systems to understand and respond to the emotional states of the users. In this work, the concept of transfer learning has been extended to the novel domain of hybrid classical-quantum neural networks for enhancing SER performance. The classical part involves preprocessing raw speech signals to generate three-channel log mel-spectrograms and the pretrained VGG 19 network for extracting useful emotional features. The quantum part is built upon a dressed quantum neural network (QNN), comprising multiple parallel QNN blocks, for accurate emotion classification. Extensive experiments on the publicly accessible TESS dataset reveal that the proposed hybrid transfer learning approach achieves state of the art accuracy of 98.93 %. An ablation study demonstrates the significant performance improvement attributed to the incorporation of QNN blocks. The integration of classical and quantum neural networks provides a robust and efficient solution, leveraging the strengths of both computational paradigms to enhance SER based applications.
Speech emotion recognition (SER) remains fragile in real-world conditions because emotional cues are subtle, speaker-dependent, and easily confounded by recording variability, while high-performing deep models typically rely on large and carefully curated training sets. Quantum machine learning offers an alternative way to introduce nonlinear correlation modeling with compact modules, yet existing quantum SER studies remain limited, and the impact of circuit structure is not well understood. This paper presents HQTN-SER, a hybrid quantum-classical framework that investigates how quantum tensor network connectivity can support SER under small-qubit settings. HQTN-SER introduces (i) an MPS-inspired quantum tensor network module that enforces structured interactions to model correlations in speech representations with a small number of trainable parameters, and (ii) a fusion strategy that combines quantum measurement features with a learned classical latent embedding for end-to-end emotion classification. We evaluate HQTN-SER on three public benchmarks (RAVDESS, SAVEE, and MDER) under a unified preprocessing and training protocol. The proposed model achieves test accuracies of 80.09\% on RAVDESS, 78.12\% on SAVEE, and 73.51\% on MDER, with corresponding macro-F1 scores of 0.8012, 0.7826, and 0.7351, respectively. The model also exhibits stable convergence while using only three or four qubits, suggesting that MPS-inspired circuit structure can be an effective and hardware-aware design choice for quantum-assisted SER. These results provide a compact experimental baseline for studying structured quantum modules in affective computing.
Quantum machine learning (QML) offers a promising avenue for advancing representation learning in complex signal domains. In this study, we investigate the use of parameterised quantum circuits (PQCs) for speech emotion recognition (SER)-a challenging task due to the subtle temporal variations and overlapping affective states in vocal signals. We propose a hybrid quantum-classical architecture that integrates PQCs into a conventional convolutional neural network (CNN), leveraging quantum properties such as superposition and entanglement to enrich emotional feature representations. Experimental evaluations on three benchmark datasets IEMOCAP, RECOLA, and MSP-IMPROV-demonstrate that our hybrid model achieves improved classification performance relative to a purely classical CNN baseline, with over 50% reduction in trainable parameters. Furthermore, Adjusted Rand Index (ARI) analysis demonstrates that the quantum model yields feature representations with improved alignment to true emotion classes compared with the classical model, reinforcing the observed performance gains. This work provides early evidence of the potential for QML to enhance emotion recognition and lays the foundation for future quantum-enabled affective computing systems.
Facial Emotion Recognition (FER) is essential for enhancing human-computer interaction and psychological analysis. Despite the progress in classical approaches, Quantum Convolutional Neural Networks (QCNNs) offer promising advancements by leveraging quantum parallelism and entanglement for more efficient feature processing. Combining the advantages of both classical and quantum domains, this study introduces a hybrid classical to enhanced QCNN (CEQCNN) framework for FER. The process begins with the pre-processing of facial images, followed by a supervised auto-encoder that leverages an additional classification loss, along with the reconstruction loss, to effectively extract discriminatively informative emotional features suitable for input to the QCNN. Traditional QCNN architectures suffer from a less expressive quantum feature space and insufficient post-pooling qubit correlation. The proposed enhanced QCNN architecture overcomes these limitations by introducing two new layers: the Expressible Convolutional Layer (Ex-Conv), which enhances quantum feature space representation utilizing a high expressibility ansatz, and the Entangled Convolutional Layer (En-Conv), which increases qubit entanglement after pooling to mitigate information loss. Extensive experimentation reveals that the supervised auto-encoder is effective for class-specific, organized feature extraction, and the combined integration of Ex-Conv and En-Conv layers within QCNN significantly improves the performance compared to traditional QCNN. Further analysis of expressibility and entangling capability justifies the effectiveness of these new layers. The proposed CEQCNN approach achieves 80.12% accuracy on FER-2013 and 91.98% on KDEF dataset, demonstrating a competitive position in the literature.
This paper proposes hybrid quantum machine learning (QML) models for automatic emotion recognition from human speech signals. The proposed quantum support vector machine (QSVM) and hybrid quantum neural network (HQNN) models use Mel-Frequency Cepstral Coefficients (MFCC) as the features extracted from the speech data. We present a detailed analysis comparing the performance of QML models to conventional machine learning models for human speech-based emotion recognition, which is a multi-class classification problem. Our results illustrate that QSVM can achieve higher classification accuracy with a much reduced number of speech signal variables compared to traditional SVMs. Furthermore, the proposed HQNN classifier outperforms classical neural networks (NN) in terms of classification accuracy while utilizing a reduced number of training parameters. We have tested the performance of the HQNN model on a real IBM quantum computer. The results indicate that QML models provide a more effective and precise method for classification tasks involving the recognition of human emotions.
Speech-based machine learning systems are sensitive to noise, complicating reliable deployment in emotion recognition and voice pathology detection. We evaluate the robustness of a hybrid quantum machine learning model, quanvolutional neural networks (QNNs) against classical convolutional neural networks (CNNs) under four acoustic corruptions (Gaussian noise, pitch shift, temporal shift, and speed variation) in a clean-train/corrupted-test regime. Using AVFAD (voice pathology) and TESS (speech emotion), we compare three QNN models (Random, Basic, Strongly) to a simple CNN baseline (CNN-Base), ResNet-18 and VGG-16 using accuracy and corruption metrics (CE, mCE, RCE, RmCE), and analyze architectural factors (circuit complexity or depth, convergence) alongside per-emotion robustness. QNNs generally outperform the CNN-Base under pitch shift, temporal shift, and speed variation (up to 22% lower CE/RCE at severe temporal shift), while the CNN-Base remains more resilient to Gaussian noise. Among quantum circuits, QNN-Basic achieves the best overall robustness on AVFAD, and QNN-Random performs strongest on TESS. Emotion-wise, fear is most robust (80-90% accuracy under severe corruptions), neutral can collapse under strong Gaussian noise (5.5% accuracy), and happy is most vulnerable to pitch, temporal, and speed distortions. QNNs also converge up to six times faster than the CNN-Base. To our knowledge, this is a systematic study of QNN robustness for speech under common non-adversarial acoustic corruptions, indicating that shallow entangling quantum front-ends can improve noise resilience while sensitivity to additive noise remains a challenge.