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

Raphael Blankson, Evgeniy Pavlovskiy

Результат исследования: Публикации в книгах, отчётах, сборниках, трудах конференцийстатья в сборнике материалов конференциинаучнаярецензирование

Аннотация

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.

Язык оригиналаанглийский
Название основной публикацииProceedings of International Conference on Data Science and Applications, ICDSA 2021
РедакторыMukesh Saraswat, Sarbani Roy, Chandreyee Chowdhury, Amir H. Gandomi
Место публикацииSingapore
ИздательSpringer Science and Business Media Deutschland GmbH
Страницы483-492
Число страниц10
Том287
ИзданиеSpringer Nature Singapore
ISBN (электронное издание)978-981-16-5348-3
ISBN (печатное издание)978-981-16-5347-6
DOI
СостояниеОпубликовано - 2022
Событие2nd International Conference on Data Science and Applications, ICDSA 2021 - Virtual, Online
Продолжительность: 10 апр. 202111 апр. 2021

Серия публикаций

НазваниеLecture Notes in Networks and Systems
Том287
ISSN (печатное издание)2367-3370
ISSN (электронное издание)2367-3389

Конференция

Конференция2nd International Conference on Data Science and Applications, ICDSA 2021
ГородVirtual, Online
Период10.04.202111.04.2021

Предметные области OECD FOS+WOS

  • 1.02 КОМПЬЮТЕРНЫЕ И ИНФОРМАЦИОННЫЕ НАУКИ

Fingerprint

Подробные сведения о темах исследования «Applying Variational Circuits in Deep Learning Architectures for Improving Discriminative Power of Speaker Embeddings». Вместе они формируют уникальный семантический отпечаток (fingerprint).

Цитировать