Speaker voice normalization for end-to-end speech translation.
Zhengshan XueTingxun ShiXiaolei ZhangDeyi XiongPublished in: Expert Syst. Appl. (2024)
Keyphrases
- end to end
- speech sounds
- prosodic features
- synthesized speech
- speech recognition
- text to speech
- speaker verification
- speech synthesis
- audio visual
- speaker recognition
- automatic speech recognition
- emotion recognition
- mel frequency cepstral coefficients
- speech signal
- speaker identification
- vocal tract
- speaker diarization
- voice activity detection
- multipath
- speech quality
- congestion control
- speaker dependent
- admission control
- ad hoc networks
- hidden markov models
- gaussian mixture model
- acoustic features
- high bandwidth
- fundamental frequency
- machine translation
- wireless ad hoc networks
- noisy environments
- scalable video
- internet protocol
- content delivery
- spontaneous speech
- rate allocation
- speaker adaptation
- language model
- application layer