J-MAC: Japanese multi-speaker audiobook corpus for speech synthesis.
Shinnosuke TakamichiWataru NakataNaoko TanjiHiroshi SaruwatariPublished in: CoRR (2022)
Keyphrases
- speech synthesis
- speech recognition
- prosodic features
- vocal tract
- text to speech
- spontaneous speech
- automatic speech recognition
- language model
- japanese language
- pattern recognition
- hidden markov models
- test set
- speaker verification
- speech signal
- speaker identification
- speech corpus
- neural network
- speaker diarization
- manually annotated
- image acquisition
- image coding
- text mining
- computer vision