StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models.
Yinghao Aaron LiCong HanVinay S. RaghavanGavin MischlerNima MesgaraniPublished in: NeurIPS (2023)
Keyphrases
- text to speech
- language model
- human level
- speech synthesis
- speech recognition
- language modeling
- artificial general intelligence
- machine intelligence
- text to speech synthesis
- prosodic features
- document retrieval
- information retrieval
- n gram
- probabilistic model
- intelligent systems
- language modelling
- query expansion
- human intelligence
- web intelligence
- test collection
- artificial intelligence
- retrieval model
- word processing
- relevance model
- statistical language models
- ai systems
- translation model
- cognitive science
- word error rate
- neural network
- database systems
- computational intelligence
- document ranking
- speech signal