0% Complete
صفحه اصلی
/
سی و یکمین کنفرانس بین المللی مهندسی برق
Improving CycleGAN-VC2 Voice Conversion by Learning MCD-Based Evaluation and Optimization
نویسندگان :
Majid Behdad
1
Davood Gharavian
2
1- دانشگاه شهید بهشتی
2- دانشگاه شهید بهشتی
کلمات کلیدی :
CycleGAN-VC،perceptual evaluation،perceptual optimization،MetricGAN،Mel-Cepstral distance،speech quality Assessment،Nisqa tool
چکیده :
Abstract—Nowadays’ voice conversion systems that convert source speakers to target speakers in a speech utterance, have various applications, and improving their quality is very important. One method that still has not attracted enough attention for the VC quality improvements is to concentrate on the optimization of the discriminators of a GAN-based VC System. In this paper, we chose Cycle-GAN-VC2 as the baseline to implement a modified version of Mel-scale human hearing-related objective evaluation metric, Modified Mel-Cepstral Distance (MMCD) to help the discriminators to better learn to judge between real and fake data. We developed and implemented our new metric MMCD that is between 0 and 1 to use it in discriminators’ loss functions. The main goal is to force the discriminators to learn the MMCD metric behavior in its judgements; while in conventional CycleGAN-VC2, discriminators work as the classifiers that decide which data is real and which one is fake without any attention to perceptual references and measures like MCD score that can be varied continuously from zero to one. Experimental results show improvements in the quality of output speech versus MCD measure despite that the training of our baseline VC system is based on a set of non-parallel data, and don’t use any time-alignment in training process. So, in parallel VC systems more improvements could be anticipated.
لیست مقالات
لیست مقالات بایگانی شده
Object Detection enhancement based on Super-Resolution Mapping
Danial Abyazi - Dadfar Abyazi - Mehran Yazdi
FGM Copula based Analysis of Outage Probability for Wireless Three-User Multiple Access Channel with Correlated Channel Coefficients
Mona Sadat Mohsenzadeh - Ghosheh Abed Hodtani
Energy Efficiency of UAV-based mmWave-mMIMO Systems Using Low-Precision ADCs
Sogol Moshirvaziri - Jamshid َAbouei
شناسایی کمپلکس های پروتئینی با رویکرد خوشه بندی EM و با استفاده از داده های زیستی
مریم مولی وردیخانی - سعید جلیلی
Efficient and Fast Analysis of SIW Microwave Devices Using the Multiple Multipole Technique
Ahmad Bakhtafrouz - Mohammad Moemenian - Mohsen Maddahali - Mohsen Karimian Kakolaki
طراحی تزویجگر پهن باند سه استابی فشرده میکرواستریپ برای استفاده در ترکیب کننده توان
صادق حیدری کاهکش - اکرم شیخی
Highly Efficient Implementation of Chaotic Systems Utilizing High-Level Synthesis Tools
Mobin Vaziri - Hadi Jahanirad
A Novel Model for Student's Mental Health Monitoring Based on Hard and Soft Data Fusion
Mohammad Fatahi - Masoud Alizadeh - Behzad Moshiri
Design and Implementation of a Modular ROS-based Mobile Robot With Hierarchical Control
Erfan Riazati - Arian Hajizadeh - Seyed Majid Esmailzadeh
Fast and Low Power Modified Carry Look-Ahead Adder
Sanaz Salem - Amir hossein Owji
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 41.7.4