Zero resource speech synthesis using transcripts derived from perceptual acoustic units.
Karthik Pandia D. SHema A. MurthyPublished in: CoRR (2020)
Keyphrases
- speech synthesis
- speech recognition
- prosodic features
- speech recognizers
- text to speech
- automatic speech recognition
- speech recognizer
- content analysis
- hidden markov models
- vocal tract
- speaker verification
- resource allocation
- resource constraints
- human perception
- resource management
- spontaneous speech
- data sets
- noisy environments
- underwater acoustic
- low level
- empirically derived