Unify and Conquer: How Phonetic Feature Representation Affects Polyglot Text-To-Speech (TTS).
Ariadna SanchezAlessio FalaiZiyao ZhangOrazio AngeliniKayoko YanagisawaPublished in: INTERSPEECH (2022)
Keyphrases
- text to speech
- feature representation
- speech synthesis
- feature extraction
- feature representations
- programming tool
- face recognition
- prosodic features
- speech recognition
- text to speech synthesis
- low dimensional
- word processing
- feature set
- sparse representation
- object detection
- image features
- spoken document retrieval
- data sets
- feature descriptors
- high dimensional
- object recognition
- pattern recognition
- image segmentation
- computer vision
- machine learning