Applying Variational Circuits in Deep Learning Architectures for Improving Discriminative Power of Speaker Embeddings

Standard

Applying Variational Circuits in Deep Learning Architectures for Improving Discriminative Power of Speaker Embeddings. / Blankson, Raphael; Pavlovskiy, Evgeniy.

Proceedings of International Conference on Data Science and Applications, ICDSA 2021. ред. / Mukesh Saraswat; Sarbani Roy; Chandreyee Chowdhury; Amir H. Gandomi. Том 287 Springer Nature Singapore. ред. Singapore : Springer Science and Business Media Deutschland GmbH, 2022. стр. 483-492 (Lecture Notes in Networks and Systems; Том 287).

Результаты исследований: Публикации в книгах, отчётах, сборниках, трудах конференций › статья в сборнике материалов конференции › научная › Рецензирование

Harvard

Blankson, R & Pavlovskiy, E 2022, Applying Variational Circuits in Deep Learning Architectures for Improving Discriminative Power of Speaker Embeddings. в M Saraswat, S Roy, C Chowdhury & AH Gandomi (ред.), Proceedings of International Conference on Data Science and Applications, ICDSA 2021. Springer Nature Singapore изд., Том. 287, Lecture Notes in Networks and Systems, Том. 287, Springer Science and Business Media Deutschland GmbH, Singapore, стр. 483-492, 2nd International Conference on Data Science and Applications, ICDSA 2021, Virtual, Online, 10.04.2021. https://doi.org/10.1007/978-981-16-5348-3_38

APA

Blankson, R., & Pavlovskiy, E. (2022). Applying Variational Circuits in Deep Learning Architectures for Improving Discriminative Power of Speaker Embeddings. в M. Saraswat, S. Roy, C. Chowdhury, & A. H. Gandomi (Ред.), Proceedings of International Conference on Data Science and Applications, ICDSA 2021 (Springer Nature Singapore ред., Том 287, стр. 483-492). (Lecture Notes in Networks and Systems; Том 287). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-16-5348-3_38

Vancouver

Blankson R, Pavlovskiy E. Applying Variational Circuits in Deep Learning Architectures for Improving Discriminative Power of Speaker Embeddings. в Saraswat M, Roy S, Chowdhury C, Gandomi AH, Редакторы, Proceedings of International Conference on Data Science and Applications, ICDSA 2021. Springer Nature Singapore ред. Том 287. Singapore: Springer Science and Business Media Deutschland GmbH. 2022. стр. 483-492. (Lecture Notes in Networks and Systems). doi: 10.1007/978-981-16-5348-3_38

Author

Blankson, Raphael ; Pavlovskiy, Evgeniy. / Applying Variational Circuits in Deep Learning Architectures for Improving Discriminative Power of Speaker Embeddings. Proceedings of International Conference on Data Science and Applications, ICDSA 2021. Редактор / Mukesh Saraswat ; Sarbani Roy ; Chandreyee Chowdhury ; Amir H. Gandomi. Том 287 Springer Nature Singapore. ред. Singapore : Springer Science and Business Media Deutschland GmbH, 2022. стр. 483-492 (Lecture Notes in Networks and Systems).

BibTeX

@inproceedings{df5c9c1eaa3b47f691341d8558ef9c7f,

title = "Applying Variational Circuits in Deep Learning Architectures for Improving Discriminative Power of Speaker Embeddings",

abstract = "Recently, the advancement in quantum technologies has had massive impact on the development of quantum algorithms on near-term quantum devices. Variational circuits, a combination of both quantum and classical algorithms, have been very useful in this advancement on near-term quantum devices. Despite these advances, most quantum applications in machine learning (deep learning) especially in transfer learning have been proof-of-concept in the qubit system and very little in the continuous-variable space but no or little application to audio data. This study applies variational circuits to practical real-life speaker classification data for the first time in the continuous-variable system. In separate experiments, the quantum model was combined with a simple convolutional neural network and ResNet18 model, respectively, and the results were compared to classical ResNet18 model applied on the same speaker dataset. The simple convolutional model outperformed the ResNet18 quantum model significantly after one epoch. Further, investigation is needed to model-specific problems that classical models cannot solve.",

keywords = "Continuous-variable quantum model, Deep learning, Quantum machine learning, Speaker classification, Variational circuit",

author = "Raphael Blankson and Evgeniy Pavlovskiy",

note = "Publisher Copyright: {\textcopyright} 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.; 2nd International Conference on Data Science and Applications, ICDSA 2021 ; Conference date: 10-04-2021 Through 11-04-2021",

year = "2022",

doi = "10.1007/978-981-16-5348-3_38",

language = "English",

isbn = "978-981-16-5347-6",

volume = "287",

series = "Lecture Notes in Networks and Systems",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "483--492",

editor = "Mukesh Saraswat and Sarbani Roy and Chandreyee Chowdhury and Gandomi, {Amir H.}",

booktitle = "Proceedings of International Conference on Data Science and Applications, ICDSA 2021",

address = "Germany",

edition = "Springer Nature Singapore",

}

RIS

TY - GEN

T1 - Applying Variational Circuits in Deep Learning Architectures for Improving Discriminative Power of Speaker Embeddings

AU - Blankson, Raphael

AU - Pavlovskiy, Evgeniy

PY - 2022

Y1 - 2022

N2 - Recently, the advancement in quantum technologies has had massive impact on the development of quantum algorithms on near-term quantum devices. Variational circuits, a combination of both quantum and classical algorithms, have been very useful in this advancement on near-term quantum devices. Despite these advances, most quantum applications in machine learning (deep learning) especially in transfer learning have been proof-of-concept in the qubit system and very little in the continuous-variable space but no or little application to audio data. This study applies variational circuits to practical real-life speaker classification data for the first time in the continuous-variable system. In separate experiments, the quantum model was combined with a simple convolutional neural network and ResNet18 model, respectively, and the results were compared to classical ResNet18 model applied on the same speaker dataset. The simple convolutional model outperformed the ResNet18 quantum model significantly after one epoch. Further, investigation is needed to model-specific problems that classical models cannot solve.

AB - Recently, the advancement in quantum technologies has had massive impact on the development of quantum algorithms on near-term quantum devices. Variational circuits, a combination of both quantum and classical algorithms, have been very useful in this advancement on near-term quantum devices. Despite these advances, most quantum applications in machine learning (deep learning) especially in transfer learning have been proof-of-concept in the qubit system and very little in the continuous-variable space but no or little application to audio data. This study applies variational circuits to practical real-life speaker classification data for the first time in the continuous-variable system. In separate experiments, the quantum model was combined with a simple convolutional neural network and ResNet18 model, respectively, and the results were compared to classical ResNet18 model applied on the same speaker dataset. The simple convolutional model outperformed the ResNet18 quantum model significantly after one epoch. Further, investigation is needed to model-specific problems that classical models cannot solve.

KW - Continuous-variable quantum model

KW - Deep learning

KW - Quantum machine learning

KW - Speaker classification

KW - Variational circuit

UR - http://www.scopus.com/inward/record.url?scp=85121691920&partnerID=8YFLogxK

UR - https://www.mendeley.com/catalogue/2a623700-7a54-35b4-ae17-6c0ccd074a7e/

U2 - 10.1007/978-981-16-5348-3_38

DO - 10.1007/978-981-16-5348-3_38

M3 - Conference contribution

AN - SCOPUS:85121691920

SN - 978-981-16-5347-6

VL - 287

T3 - Lecture Notes in Networks and Systems

SP - 483

EP - 492

BT - Proceedings of International Conference on Data Science and Applications, ICDSA 2021

A2 - Saraswat, Mukesh

A2 - Roy, Sarbani

A2 - Chowdhury, Chandreyee

A2 - Gandomi, Amir H.

PB - Springer Science and Business Media Deutschland GmbH

CY - Singapore

T2 - 2nd International Conference on Data Science and Applications, ICDSA 2021

Y2 - 10 April 2021 through 11 April 2021

ER -

ID: 35178175