LRSpeech: Extremely Low-Resource Speech Synthesis and Recognition.
Jin XuXu TanYi RenTao QinJian LiSheng ZhaoTie-Yan LiuPublished in: KDD (2020)
Keyphrases
- speech synthesis
- speech corpus
- speech recognition
- recognition rate
- text to speech
- recognition accuracy
- object recognition
- low error rates
- prosodic features
- automatic recognition
- pattern recognition
- vocal tract
- resource allocation
- recognition algorithm
- action recognition
- feature extraction
- image recognition
- web resources
- resource management
- gesture recognition
- activity recognition
- face recognition
- high levels
- recognition process
- noisy environments
- data sets
- recognition scheme
- information resources
- image matching
- feature selection