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

arXiv:2601.02432

Quantifying Quanvolutional Neural Networks Robustness for Speech in Healthcare Applications

Ha Tran, Bipasha Kashyap, Pubudu Nishantha Pathirana

Published Jan 5, 2026• 0 citations
arXivHTMLPDF

Abstract

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.

DOI
10.48550/arxiv.2601.02432

Related papers

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 +2 more

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.

International Conference on Computer and Information Technology (ICCIT)•Dec 19, 2025•0 citations

Quantum Approaches for Dysphonia Assessment in Small Speech Datasets

Ha Tran, Bipasha Kashyap, Pubudu Nishantha Pathirana

Dysphonia, a prevalent medical condition, leads to voice loss, hoarseness, or speech interruptions. To assess it, researchers have been investigating various machine learning techniques alongside traditional medical assessments. Convolutional Neural Networks (CNNs) have gained popularity for their success in audio classification and speech recognition. However, the limited availability of speech data, poses a challenge for CNNs. This study compares the performance of CNNs with standard convolutional layers, CNNs with random nonlinear convolutional layers (RANDOM models), and a novel hybrid quantum-classical architecture, Quanvolutional Neural Networks (QNNs), which are well-suited for small datasets. The audio data was preprocessed into Mel spectrograms, comprising 243 training samples and 61 testing samples in total, and used in four experiments. A total of six models were developed: two CNNs, two RANDOM models, and two QNNs, with the second models incorporating additional layers to boost performance. The angle encoding method was employed within the quanvolutional layer, which is the quantum transformation layer of the QNNs, to enable the representation of more complex features of Mel spectrogram. The experimental results demonstrated that QNN models consistently outperformed the CNN models in both classification accuracy (ranging from 82.22% ± 4% to 89.26% ± 2%) and convergence speed across all four experiments.Clinical relevance- This work investigates the potential of quantum-based approaches for medical data classification and their promising role in enhancing dysphonia assessment.

arXiv:2502.08968•Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)•Jul 14, 2025•4 citations

Evaluating Accuracy and Adversarial Robustness of Quanvolutional Neural Networks

Korn Sooksatra, Pablo Rivas, Javier Orduz

Machine learning can thrust technological advances and benefit different application areas. Further, with the rise of quantum computing, machine learning algorithms have begun to be implemented in a quantum environment; this is now referred to as quantum machine learning. There are several attempts to implement deep learning in quantum computers. Nevertheless, they were not entirely successful. Then, a convolutional neural network (CNN) combined with an additional quanvolutional layer was discovered and called a quanvolutional neural network (QNN). A QNN has shown a higher performance over a classical CNN. As a result, QNNs could achieve better accuracy and loss values than the classical ones and show their robustness against adversarial examples generated from their classical versions. This work aims to evaluate the accuracy, loss values, and adversarial robustness of QNNs compared to CNNs.

International Conference on Computational Science and Computational Intelligence (CSCI)•Dec 1, 2021•13 citations

Quantum AI in Speech Emotion Recognition

Michael Norval, Zenghui Wang

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.

Entropy•Nov 26, 2025•5 citations

A Hybrid Quantum–Classical Deep Learning Approach for Image Recognition: Performance Analysis of Quanvolution-Based Convolutional Models

James William Carter, Emily Rose Thompson

The integration of quantum computing principles with classical deep learning architectures has emerged as a promising direction for advancing image recognition systems beyond the limitations of purely classical convolutional neural networks (CNNs). This study proposes and analyzes a hybrid quantum–classical deep learning framework based on quanvolutional neural network (QNN) principles, where quantum circuits are embedded within convolutional feature extraction layers to enhance representation capability. The research investigates how quantum-enhanced filters, particularly quanvolutional layers, contribute to improved feature diversity, non-linear transformation capacity, and classification accuracy in image recognition tasks. Building upon established convolutional architectures and quantum machine learning theories, the proposed framework integrates quantum random circuit encoding with classical deep neural networks to evaluate performance gains in comparison to conventional CNN models. The study further incorporates theoretical insights from hybrid quantum-classical learning systems, emphasizing the role of parameterized quantum circuits in feature mapping and optimization stability. The methodology is grounded in NISQ-era quantum computing constraints and leverages hybrid optimization strategies to ensure computational feasibility. Experimental evaluation demonstrates that quanvolution-based models can provide improved robustness in feature extraction, particularly in high-dimensional image spaces, while maintaining competitive computational efficiency. However, scalability limitations and noise sensitivity in quantum circuits remain key challenges. Overall, this work contributes to the growing field of quantum-enhanced machine learning by providing a structured performance analysis of hybrid quanvolutional architectures and highlighting their potential role in next-generation intelligent visual recognition systems.

International Journal of Intelligent Data and Machine Learning•Jun 1, 2026•0 citations

A Comprehensive Analysis of Accuracy and Robustness in Quantum Neural Networks

Ban Q. Tran, Duong M. Chu, Hai T. D. Pham +3 more

Quantum Machine Learning (QML) has recently emerged as a highly promising research frontier. Within this domain, Quantum Neural Networks (QNNs),characterized by Variational Quantum Circuits (VQCs) at their core and featuring layers of quantum gates optimized by classical algorithms, have garnered significant attention. However, a rigorous and exhaustive evaluation of their practical performance remains largely incomplete. In this study, we conduct a comprehensive comparative analysis of three prominent hybrid classical-quantum architectures: Quantum Convolutional Neural Networks (QCNN), Quantum Recurrent Neural Networks (QRNN), and Quantum Vision Transformers (QViT), focusing on the critical dimensions of generalization, accuracy, and robustness. Our findings provide novel insights that address previous evaluative gaps. Notably, while these models exhibit exceptional performance on low-feature datasets such as MNIST, their learning efficacy degrades significantly when transitioned to high-feature datasets. Furthermore, convolutional-based models like QCNN appear less effective on high-dimensional data than other machine learning architectures. Additionally, while all models are susceptible to adversarial noise, traditional architectures, such as recurrent and convolutional networks, demonstrate superior resilience. Conversely, in the presence of quantum noise, the transformer-based architecture proves its strength by maintaining high robustness against measurement noise, channel noise, and finite-shot effects, whereas other architectures suffer marked performance declines. These results provide a granular perspective on the current state of the field and underscore the critical importance of tailoring model selection to the constraints of contemporary Noisy Intermediate-Scale Quantum (NISQ) environments.

quant-pharXiv:2604.26110•Apr 30, 2026•0 citations
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.
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.
Dysphonia, a prevalent medical condition, leads to voice loss, hoarseness, or speech interruptions. To assess it, researchers have been investigating various machine learning techniques alongside traditional medical assessments. Convolutional Neural Networks (CNNs) have gained popularity for their success in audio classification and speech recognition. However, the limited availability of speech data, poses a challenge for CNNs. This study compares the performance of CNNs with standard convolutional layers, CNNs with random nonlinear convolutional layers (RANDOM models), and a novel hybrid quantum-classical architecture, Quanvolutional Neural Networks (QNNs), which are well-suited for small datasets. The audio data was preprocessed into Mel spectrograms, comprising 243 training samples and 61 testing samples in total, and used in four experiments. A total of six models were developed: two CNNs, two RANDOM models, and two QNNs, with the second models incorporating additional layers to boost performance. The angle encoding method was employed within the quanvolutional layer, which is the quantum transformation layer of the QNNs, to enable the representation of more complex features of Mel spectrogram. The experimental results demonstrated that QNN models consistently outperformed the CNN models in both classification accuracy (ranging from 82.22% ± 4% to 89.26% ± 2%) and convergence speed across all four experiments.Clinical relevance- This work investigates the potential of quantum-based approaches for medical data classification and their promising role in enhancing dysphonia assessment.
Machine learning can thrust technological advances and benefit different application areas. Further, with the rise of quantum computing, machine learning algorithms have begun to be implemented in a quantum environment; this is now referred to as quantum machine learning. There are several attempts to implement deep learning in quantum computers. Nevertheless, they were not entirely successful. Then, a convolutional neural network (CNN) combined with an additional quanvolutional layer was discovered and called a quanvolutional neural network (QNN). A QNN has shown a higher performance over a classical CNN. As a result, QNNs could achieve better accuracy and loss values than the classical ones and show their robustness against adversarial examples generated from their classical versions. This work aims to evaluate the accuracy, loss values, and adversarial robustness of QNNs compared to CNNs.
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.
The integration of quantum computing principles with classical deep learning architectures has emerged as a promising direction for advancing image recognition systems beyond the limitations of purely classical convolutional neural networks (CNNs). This study proposes and analyzes a hybrid quantum–classical deep learning framework based on quanvolutional neural network (QNN) principles, where quantum circuits are embedded within convolutional feature extraction layers to enhance representation capability. The research investigates how quantum-enhanced filters, particularly quanvolutional layers, contribute to improved feature diversity, non-linear transformation capacity, and classification accuracy in image recognition tasks. Building upon established convolutional architectures and quantum machine learning theories, the proposed framework integrates quantum random circuit encoding with classical deep neural networks to evaluate performance gains in comparison to conventional CNN models. The study further incorporates theoretical insights from hybrid quantum-classical learning systems, emphasizing the role of parameterized quantum circuits in feature mapping and optimization stability. The methodology is grounded in NISQ-era quantum computing constraints and leverages hybrid optimization strategies to ensure computational feasibility. Experimental evaluation demonstrates that quanvolution-based models can provide improved robustness in feature extraction, particularly in high-dimensional image spaces, while maintaining competitive computational efficiency. However, scalability limitations and noise sensitivity in quantum circuits remain key challenges. Overall, this work contributes to the growing field of quantum-enhanced machine learning by providing a structured performance analysis of hybrid quanvolutional architectures and highlighting their potential role in next-generation intelligent visual recognition systems.
Quantum Machine Learning (QML) has recently emerged as a highly promising research frontier. Within this domain, Quantum Neural Networks (QNNs),characterized by Variational Quantum Circuits (VQCs) at their core and featuring layers of quantum gates optimized by classical algorithms, have garnered significant attention. However, a rigorous and exhaustive evaluation of their practical performance remains largely incomplete. In this study, we conduct a comprehensive comparative analysis of three prominent hybrid classical-quantum architectures: Quantum Convolutional Neural Networks (QCNN), Quantum Recurrent Neural Networks (QRNN), and Quantum Vision Transformers (QViT), focusing on the critical dimensions of generalization, accuracy, and robustness. Our findings provide novel insights that address previous evaluative gaps. Notably, while these models exhibit exceptional performance on low-feature datasets such as MNIST, their learning efficacy degrades significantly when transitioned to high-feature datasets. Furthermore, convolutional-based models like QCNN appear less effective on high-dimensional data than other machine learning architectures. Additionally, while all models are susceptible to adversarial noise, traditional architectures, such as recurrent and convolutional networks, demonstrate superior resilience. Conversely, in the presence of quantum noise, the transformer-based architecture proves its strength by maintaining high robustness against measurement noise, channel noise, and finite-shot effects, whereas other architectures suffer marked performance declines. These results provide a granular perspective on the current state of the field and underscore the critical importance of tailoring model selection to the constraints of contemporary Noisy Intermediate-Scale Quantum (NISQ) environments.