编程之家

SpeechSynthesis实现页面内容语音播报

speech

Ngram Models in TexttoSpeech Synthesis: Creating NaturalSounding Voices

delmodmodemodelmodelsnatramspeechtextextvoice

策略梯度与SpeechRecognition

chrspeech

Speech recognition with deep recurrent neural networks_2013.Alex Graves

neural networkspeech

# ext-to-speech|tts|voice-cloning|AIGC|多模态#有图文部署GPT-SoVits：上线一周就获得了4.1k star！效果炸裂的开源跨语言音色克隆模型！

speechstatarvoice

Android 标准语音识别框架：SpeechRecognizer | 开发者说·DTalk

chrroispeech