MOS Predictor for Synthetic Speech with I-Vector Inputs.
Miao LiuJing WangShicong LiFei XiangYue YaoLidong YangPublished in: ICASSP (2022)
Keyphrases
- speech recognition
- neural network
- real world
- audio visual
- vector space
- speech signal
- pattern recognition
- feature vectors
- signal processing
- automatic speech recognition
- real images are presented
- language acquisition
- vector data
- text to speech synthesis
- modular neural network
- english text
- text to speech
- broadcast news
- dialogue system
- real scenes
- information retrieval