Daft-Exprt: Cross-Speaker Prosody Transfer on Any Text for Expressive Speech Synthesis.
Julian ZaïdiHugo SeutéBenjamin van NiekerkMarc-André CarbonneauPublished in: INTERSPEECH (2022)
Keyphrases
- speech synthesis
- text to speech
- prosodic features
- speech recognition
- vocal tract
- automatic speech recognition
- language model
- speech corpus
- hidden markov models
- transfer learning
- pattern recognition
- text mining
- information retrieval
- spontaneous speech
- word processing
- speaker diarization
- speaker identification
- speech signal
- noisy environments
- database
- neural network
- document analysis
- textual data
- speaker recognition
- cross domain
- web documents
- feature vectors
- computer vision
- machine learning
- data mining