首页>
外国专利>
METHOD AND COMPUTER READABLE STORAGE MEDIUM FOR PERFORMING TEXT-TO-SPEECH SYNTHESIS USING MACHINE LEARNING BASED ON SEQUENTIAL PROSODY FEATURE
METHOD AND COMPUTER READABLE STORAGE MEDIUM FOR PERFORMING TEXT-TO-SPEECH SYNTHESIS USING MACHINE LEARNING BASED ON SEQUENTIAL PROSODY FEATURE
展开▼
机译:用于使用基于顺序韵律特征的机器学习进行文本与语音合成的方法和计算机可读存储介质
展开▼
页面导航
摘要
著录项
摘要
The present disclosure relates to a text-to-speech synthesis method using machine learning based on sequential prosody features. Text-to-speech synthesis using machine learning based on sequential prosody features includes the steps of receiving input text, receiving sequential prosody features, and artificial neural network text-to-speech synthesis using input text and received sequential prosody features and generating output speech data for the input text in which the received sequential prosody features are reflected by input to the model.
展开▼