Sparse representation-based quasi-clean speech construction for speech quality assessment under complex environments.
Weili ZhouQianhua HeYalou WangYanxiong LiPublished in: IET Signal Process. (2017)
Keyphrases
- quality assessment
- complex environments
- speech recognition
- image and video processing
- image quality assessment
- speech signal
- machine learning
- face recognition
- automatic evaluation
- image quality
- sparse representation
- autonomous agents
- data mining
- perceived quality
- data sets
- video quality
- human visual system
- visual quality
- visual information
- image retrieval
- multi agent systems
- multi agent