Normalization Driven Zero-Shot Multi-Speaker Speech Synthesis.
Neeraj KumarSrishti GoelAnkur NarangBrejesh LallPublished in: Interspeech (2021)
Keyphrases
- speech synthesis
- speech recognition
- prosodic features
- vocal tract
- text to speech
- automatic speech recognition
- pattern recognition
- speaker identification
- language model
- hidden markov models
- databases
- speech signal
- preprocessing
- speaker recognition
- real time
- visual features
- noisy environments
- object recognition
- case study
- genetic algorithm
- normalization method
- machine learning
- speaker dependent
- speech corpus