Improving Mandarin End-to-End Speech Synthesis by Self-Attention and Learnable Gaussian Bias.
Fengyu YangShan YangPengcheng ZhuPengju YanLei XiePublished in: ASRU (2019)
Keyphrases
- end to end
- speech synthesis
- speech recognition
- prosodic features
- text to speech
- vocal tract
- hidden markov models
- congestion control
- multipath
- high bandwidth
- admission control
- wireless ad hoc networks
- language model
- pattern recognition
- speech signal
- content delivery
- text localization and recognition
- noisy environments
- automatic speech recognition
- bitstream
- ad hoc networks
- broadcast news
- image quality
- wireless sensor networks
- computer vision
- machine learning
- real world
- real time