GLGAN-VC:一个基于损失的指导生成对抗网络,用于许多对许多语音转换.
IEEE transactions on neural networks and learning systems
|December 4, 2023
概括
本研究介绍了GLGAN-VC,它是一种生成对抗网络 (GAN) 系统,通过增强语音自然性和说话者相似性,显著改善了多对多语音转换 (VC). 这种新的方法在产生高质量,自然听起来的转换语音方面取得了最先进的结果.
科学领域:
- 语音处理和人工智能.
- 机器学习用于音频合成.
- 深度学习在信号处理中的应用.
背景情况:
- 许多对许多语音转换 (VC) 旨在在保留语音内容的同时,在扬声器之间传输语音特征.
- 现有的VC方法经常与自然性作斗争,在原始语音和转换语音之间造成差距.
- 在并行和非并行VC场景中改善自然性存在重大潜力.
研究的目的:
- 通过提高语音自然性和说话者相似性来增强多对多的语音转换 (VC).
- 引入一个新的生成对抗网络 (GAN) 系统,GLGAN-VC,具有架构和损失功能的改进.
- 解决当前VC技术在生成现实和高保真语音方面的局限性.
主要方法:
- 开发了一个名为GLGAN-VC.的生成对抗网络 (GAN) 系统.
- 整合了一台双向下采样和上采样 (PDU) 发生器,用于有效的语音特征映射 (FM).
- 利用FM损失来保存内容,基于剩余连接 (RC) 的区分器来改善学习,以及用于捕捉扬声器特征差异的引导损失 (GL) 功能.
- 提出了增强的重建损失,以更好地保存上下文信息.
主要成果:
- 与最先进的 (SOTA) 基于GAN的多对多的VC模型相比,GLGAN-VC模型表现出卓越的性能.
- 对VCC 2016,VCC 2018,VCC 2020和ESD数据集的评估显示,生成语音质量的显著改善.
- 主观和客观指标都证实了演讲者的相似性和整体演讲的自然性.
结论:
- 拟议的GLGAN-VC系统有效地增强了多对多的语音转换.
- 整合PDU发电机,FM损失,RC区分器和引导损失有助于优越的语音质量和扬声器相似性.
- 这项研究通过提供更自然,更准确的语音合成方法,推进了语音转换领域.
更多相关视频
06:24Author Spotlight: Advancements in the Fabrication of Synthetic Vocal Fold Models for Phonetic and Robotic Applications
Published on: January 5, 2024
865
09:09Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody
Published on: September 27, 2024
460
相关概念视频
Reducing Line Loss
155
In a three-phase circuit, line loss is an indicator of energy dissipated as heat due to the resistance of transmission lines. To address this, incorporating transformers into the system—a step-up transformer at the source and a step-down transformer at the load—is a strategic solution. Two three-phase transformers are introduced to improve this.
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
155
Improving Translational Accuracy
2.6K
2.6K
Line Loss
246
The different configurations of source-load connections include wye (star) and delta connections. The relationship between line and phase voltages and currents varies depending on the configuration. When the source is supplying power, it is transmitted through the wires to the load, and during this transmission, some power is absorbed by the wires, leading to line loss.
Line loss impacts power delivery efficiency in a balanced three-phase circuit. The symmetry in such a circuit simplifies the...
Line loss impacts power delivery efficiency in a balanced three-phase circuit. The symmetry in such a circuit simplifies the...
246
Air-entraining Agents
80
Air-entraining agents improve the durability and workability of concrete in climates with frequent freezing and thawing. These agents prevent cracks by introducing small air bubbles into the mix, creating spaces accommodating water expansion when temperatures drop. The air-entraining agents lower the surface tension of water, forming stable, small air bubbles. This method is more effective than having accidental large voids, as the intentional, smaller, and evenly distributed air voids improve...
80
Masking and Demasking Agents
2.4K
EDTA titrations may necessitate masking and demasking agents to temporarily protect a particular metal ion in a mixture from the EDTA reaction. These agents facilitate the sequential analysis of the metal ions by forming stable complexes with some—but not all—metal ions during certain steps.
There are many masking agents, such as cyanide, fluoride, triethanolamine, thiourea, and 2,3-bis(sulfanyl)propan-1-ol (formerly 2,3-dimercapto-1-propanol), with the masking agent chosen based on...
There are many masking agents, such as cyanide, fluoride, triethanolamine, thiourea, and 2,3-bis(sulfanyl)propan-1-ol (formerly 2,3-dimercapto-1-propanol), with the masking agent chosen based on...
2.4K
Gene Conversion
9.8K
Other than maintaining genome stability via DNA repair, homologous recombination plays an important role in diversifying the genome. In fact, the recombination of sequences forms the molecular basis of genomic evolution. Random and non-random permutations of genomic sequences create a library of new amalgamated sequences. These newly formed genomes can determine the fitness and survival of cells. In bacteria, homologous and non-homologous types of recombination lead to the evolution of new...
9.8K
