Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale.
Matthew LeApoorv VyasBowen ShiBrian KarrerLeda SariRashel MoritzMary WilliamsonVimal ManoharYossi AdiJay MahadeokarWei-Ning HsuPublished in: NeurIPS (2023)
Keyphrases
- text generation
- multi lingual
- natural language generation
- text to speech
- text recognition
- english text
- natural language
- text to speech synthesis
- text mining
- speech recognition
- language independent
- dialogue system
- speech synthesis
- text retrieval
- lexical features
- scale space
- information retrieval
- text documents
- automatic speech recognition
- natural language processing
- information access
- text input
- language generation
- web documents
- speech signal
- hidden markov models
- digital libraries
- vocal tract
- spontaneous speech