光谱图
波形
语音识别
计算机科学
钥匙(锁)
性格(数学)
特征(语言学)
代表(政治)
语音合成
人工神经网络
序列(生物学)
持续时间(音乐)
人工智能
模式识别(心理学)
声学
数学
生物
物理
语言学
电信
哲学
几何学
政治学
雷达
法学
政治
遗传学
计算机安全
作者
Jonathan Shen,Ruoming Pang,Ron Weiss,Mike Schuster,Navdeep Jaitly,Zongheng Yang,Zhifeng Chen,Yu Zhang,Yu-Xuan Wang,RJ Skerry-Ryan,Rif A. Saurous,Yannis Agiomyrgiannakis,Yonghui Wu
出处
期刊:Cornell University - arXiv
日期:2017-12-15
被引量:47
标识
DOI:10.48550/arxiv.1712.05884
摘要
This paper describes Tacotron 2, a neural network architecture for speech synthesis directly from text. The system is composed of a recurrent sequence-to-sequence feature prediction network that maps character embeddings to mel-scale spectrograms, followed by a modified WaveNet model acting as a vocoder to synthesize timedomain waveforms from those spectrograms. Our model achieves a mean opinion score (MOS) of $4.53$ comparable to a MOS of $4.58$ for professionally recorded speech. To validate our design choices, we present ablation studies of key components of our system and evaluate the impact of using mel spectrograms as the input to WaveNet instead of linguistic, duration, and $F_0$ features. We further demonstrate that using a compact acoustic intermediate representation enables significant simplification of the WaveNet architecture.
科研通智能强力驱动
Strongly Powered by AbleSci AI