Real-Time Single-Speaker Taiwanese-Accented Mandarin Speech Synthesis System.
Yih-Wen WangChia-Ping ChenPublished in: ROCLING (2020)
Keyphrases
- speech synthesis
- prosodic features
- speech recognition
- real time
- text to speech
- vocal tract
- speaker verification
- pattern recognition
- speech corpus
- language model
- automatic speech recognition
- speech signal
- speaker independent
- low cost
- hidden markov models
- speaker identification
- language learning
- computer vision
- machine learning
- university students
- quality of service
- speaker diarization
- control system