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

Modern Physics Letters B

An efficient speaker recognition using quantum neural network

Rupinderdeep Kaur, Richa Sharma, Parteek Kumar

Published Nov 2, 2018• 8 citations
Publisher

Abstract

Speaker recognition is the technique to identify the identity of a person from statistical features obtained from speech signals. Many speaker recognition techniques have been designed and implemented so far to efficiently recognize the speaker. From the existing review, it is found that the existing speaker recognition techniques suffer from the over-fitting issues. Therefore, to overcome the over-fitting issue in this paper, we design, a novel ensemble-based quantum neural network. It selects one base model (i.e. expert) for each query, and concentrates on inductive bias reduction. A set of quantum neural networks are trained by considering different kinds of quantum features and are afterwards used to recognize the speaker. In the end, ensembling is used to combine these classification results. Extensive experiments have been carried out by considering the proposed technique and existing competitive machine learning-based speaker recognition techniques on speaker recognition data. It is observed that the proposed technique outperforms existing speaker recognition techniques in terms of accuracy and sensitivity by 1.371% and 1.291%, respectively.

DOI
10.1142/s0217984918503840

Related papers

Quantum neural network in speech recognition

Fei Li, Shengmei Zhao, Baoyu Zheng

This paper describes a new kind of neural network - quantum neural network (QNN) and its application to recognition of continuous digits. QNN combines the advantages of neural modeling and fuzzy theoretic principles. Experiment results show that more than 15% error reduction is achieved on a speaker-independent continuous digits recognition task compared with the backpropagation (BP) network.

International Conference on Signal Processing•Oct 1, 2003•36 citations

Speech Recognition Using Quantum Convolutional Neural Network

B Thejha, S Yogeswari, A Vishalli +1 more

Quantum machine learning (QML) has emerged as an exciting new technology that explores challenging machine learning issues by relying on advances in quantum computing. A convolutional neural network is primarily used in the classical portion of the QNN-based Speech Recognition System, which is made up of both classical and quantum components. The quantum component is based on the equation’s quantum circuits with a certain learnable parameter. Speech recognition technology is one of the quickly evolving technologies, along with Siri on the iPhone, chatbots, Alexa on the Amazon Echo, etc… The research uses a quantum convolutional neural network (QCNN) to identify voice and convert it to text. The use of Quantum filters will reduce the input in to qubits and then it will be further moving in to the feature extraction and classification process. QCNN gives more accurate results and will increase the scalability by adding more layers in to the model.

International Conference on Science Technology Engineering and Mathematics (ICONSTEM)•Apr 6, 2023•11 citations

Recognition of Continuous Digits by Quantum Neural Networks

Lifei

This paper describes a new kind of neural network-Quantum Neural Network (QNN) and its application to recognition of continuous digits. QNN combines the advantages of neural modeling and fuzzy theoretic principles. Experiment results show that more than 15 percent error reduction is achieved on a speaker-independent continuous digits recognition task compared with BP networks.

中国邮电高校学报:英文版•Jan 1, 2003•0 citations

Quantum Neural Networks for Pattern Recognition and Prediction

Oscar Muller, Elena Schmidt, Anna Horvath

Quantum neural networks (QNNs) -- parameterised quantum circuits trained to perform pattern recognition and predictive tasks -- represent a prominent but contested direction in quantum machine learning, offering potential parameter efficiency and expressibility benefits over classical neural networks for specific problem structures while suffering from barren plateau trainability limitations at scale. The 2024 issue of this journal established SNAD LSAD-structured ansatz (Silva et al., 2024) as the critical enabler of scalable QNN training, and QHDC (Bianchi et al., 2024) showed that QNN advantage is dataset-dependent. This paper advances the QNN field with the Quantum Neural Network Design and Evaluation (QNNDE) framework, a systematic methodology for QNN architecture design, training optimisation, and performance evaluation across four pattern recognition and prediction task classes: temporal sequence modelling (quantum recurrent circuits), spatial pattern recognition (quantum convolutional circuits), generative modelling (quantum generative adversarial networks), and time-series regression (quantum reservoir computing). QNNDE is evaluated on eight benchmark tasks spanning physics simulation, molecular property prediction, quantum state tomography, financial time-series, medical signal classification, and quantum circuit synthesis on IBM Quantum Eagle (127-qubit) and IonQ Forte (35-qubit). Quantum recurrent circuits achieve 12.4pp accuracy improvement over classical LSTMs for quantum state evolution prediction. Quantum convolutional circuits match classical CNNs on image-derived molecular patterns at 68.4% parameter reduction. Quantum GANs generate molecular conformations with 8.4% lower FID than classical GAN at equal network size. Quantum reservoir computing outperforms classical echo state networks by 18.4% on quantum-process time-series prediction.

Quantum Frontiers Journal•Mar 28, 2025•0 citations

Handwritten numeral recognition with a quantum neural network model

Mao Yaxuan, Kazuyuki Aihara

Handwritten numeral recognition has generated significant interest in last several years owing to its sundry application potentials in the fields of image processing and computer vision. Recently, quantum neural networks (QNN) have been found to be efficient for information processing, such as image classification, recognition and optimization, owing to its distinct features. Therefore, in this study, a QNN based handwritten character recognition system is studied. Experiments are conducted with the data from the MNIST database. Back-propagation (BP) algorithm and particle swarm optimization (PSO) algorithm are used during the training process to improve the performance of the QNN. The resulting recognition rate of this proposed system is up to 99.16%. The results of the experiments clearly demonstrate the superiority of the proposed QNN in terms of its convergence speed and recognition rate as compared to other classical recognition methods, and simultaneously show the superiority of the QNN in solving character recognition problems.

IEEE Information Technology, Networking, Electronic and Automation Control Conference (ITNEC)•Dec 1, 2017•0 citations

Quantum Neural Network in Recognition of Handwritten Numerals

Jie Zhou, QIANG GAN, Adam Krzyżak +1 more

This paper adopts a new kind of neural network — Quantum Neural Network (QNN) to recognize handwritten numerals. QNN combines the advantages of neural modelling and fuzzy theoretic principles. Novel experiments have been designed for the in-depth studies of applying the QNN to both synthesized confusing images and real data. Tests on synthesized data examine QNN's fuzzy feature space with an intention to illustrate its mechanism and characteristics, while studies on real data prove its great potential as a handwritten numeral classifier and the special role it plays in the multi-expert systems. Detailed comparisons and analyses of experimental results are given. An effective decision-fusion system is proposed and high reliability of 99.10% has been accomplished.

Series in machine perception and artificial intelligence•Jun 1, 1999•6 citations
Speaker recognition is the technique to identify the identity of a person from statistical features obtained from speech signals. Many speaker recognition techniques have been designed and implemented so far to efficiently recognize the speaker. From the existing review, it is found that the existing speaker recognition techniques suffer from the over-fitting issues. Therefore, to overcome the over-fitting issue in this paper, we design, a novel ensemble-based quantum neural network. It selects one base model (i.e. expert) for each query, and concentrates on inductive bias reduction. A set of quantum neural networks are trained by considering different kinds of quantum features and are afterwards used to recognize the speaker. In the end, ensembling is used to combine these classification results. Extensive experiments have been carried out by considering the proposed technique and existing competitive machine learning-based speaker recognition techniques on speaker recognition data. It is observed that the proposed technique outperforms existing speaker recognition techniques in terms of accuracy and sensitivity by 1.371% and 1.291%, respectively.
Quantum machine learning (QML) has emerged as an exciting new technology that explores challenging machine learning issues by relying on advances in quantum computing. A convolutional neural network is primarily used in the classical portion of the QNN-based Speech Recognition System, which is made up of both classical and quantum components. The quantum component is based on the equation’s quantum circuits with a certain learnable parameter. Speech recognition technology is one of the quickly evolving technologies, along with Siri on the iPhone, chatbots, Alexa on the Amazon Echo, etc… The research uses a quantum convolutional neural network (QCNN) to identify voice and convert it to text. The use of Quantum filters will reduce the input in to qubits and then it will be further moving in to the feature extraction and classification process. QCNN gives more accurate results and will increase the scalability by adding more layers in to the model.
Quantum neural networks (QNNs) -- parameterised quantum circuits trained to perform pattern recognition and predictive tasks -- represent a prominent but contested direction in quantum machine learning, offering potential parameter efficiency and expressibility benefits over classical neural networks for specific problem structures while suffering from barren plateau trainability limitations at scale. The 2024 issue of this journal established SNAD LSAD-structured ansatz (Silva et al., 2024) as the critical enabler of scalable QNN training, and QHDC (Bianchi et al., 2024) showed that QNN advantage is dataset-dependent. This paper advances the QNN field with the Quantum Neural Network Design and Evaluation (QNNDE) framework, a systematic methodology for QNN architecture design, training optimisation, and performance evaluation across four pattern recognition and prediction task classes: temporal sequence modelling (quantum recurrent circuits), spatial pattern recognition (quantum convolutional circuits), generative modelling (quantum generative adversarial networks), and time-series regression (quantum reservoir computing). QNNDE is evaluated on eight benchmark tasks spanning physics simulation, molecular property prediction, quantum state tomography, financial time-series, medical signal classification, and quantum circuit synthesis on IBM Quantum Eagle (127-qubit) and IonQ Forte (35-qubit). Quantum recurrent circuits achieve 12.4pp accuracy improvement over classical LSTMs for quantum state evolution prediction. Quantum convolutional circuits match classical CNNs on image-derived molecular patterns at 68.4% parameter reduction. Quantum GANs generate molecular conformations with 8.4% lower FID than classical GAN at equal network size. Quantum reservoir computing outperforms classical echo state networks by 18.4% on quantum-process time-series prediction.
Handwritten numeral recognition has generated significant interest in last several years owing to its sundry application potentials in the fields of image processing and computer vision. Recently, quantum neural networks (QNN) have been found to be efficient for information processing, such as image classification, recognition and optimization, owing to its distinct features. Therefore, in this study, a QNN based handwritten character recognition system is studied. Experiments are conducted with the data from the MNIST database. Back-propagation (BP) algorithm and particle swarm optimization (PSO) algorithm are used during the training process to improve the performance of the QNN. The resulting recognition rate of this proposed system is up to 99.16%. The results of the experiments clearly demonstrate the superiority of the proposed QNN in terms of its convergence speed and recognition rate as compared to other classical recognition methods, and simultaneously show the superiority of the QNN in solving character recognition problems.
This paper adopts a new kind of neural network — Quantum Neural Network (QNN) to recognize handwritten numerals. QNN combines the advantages of neural modelling and fuzzy theoretic principles. Novel experiments have been designed for the in-depth studies of applying the QNN to both synthesized confusing images and real data. Tests on synthesized data examine QNN's fuzzy feature space with an intention to illustrate its mechanism and characteristics, while studies on real data prove its great potential as a handwritten numeral classifier and the special role it plays in the multi-expert systems. Detailed comparisons and analyses of experimental results are given. An effective decision-fusion system is proposed and high reliability of 99.10% has been accomplished.