Problem-Agnostic Speech Embeddings for Multi-Speaker Text-to-Speech with SampleRNN.
David ÁlvarezSantiago PascualAntonio BonafontePublished in: SSW (2019)
Keyphrases
- text to speech
- prosodic features
- speech synthesis
- vocal tract
- text to speech synthesis
- programming tool
- multimodal interaction
- speaker verification
- english text
- word processing
- speech recognition
- vector space
- pattern recognition
- speaker recognition
- automatic speech recognition
- visual speech
- visual features
- general purpose
- hidden markov models