Mix and Match: An Empirical Study on Training Corpus Composition for Polyglot Text-To-Speech (TTS).
Ziyao ZhangAlessio FalaiAriadna SanchezOrazio AngeliniKayoko YanagisawaPublished in: INTERSPEECH (2022)
Keyphrases
- text to speech
- training corpus
- text classification
- speech synthesis
- part of speech
- training data
- statistical machine translation
- text to speech synthesis
- prosodic features
- word processing
- programming tool
- translation model
- writing skills
- pos tagging
- data mining
- parameter estimation
- text categorization
- clustering algorithm
- knowledge base
- feature selection
- artificial intelligence