Speaker-Aware Target Speaker Enhancement by Jointly Learning with Speaker Embedding Extraction.
Xuan JiMeng YuChunlei ZhangDan SuTao YuXiaoyu LiuDong YuPublished in: ICASSP (2020)
Keyphrases
- audio visual
- speech recognition
- speaker recognition
- learning process
- speaker verification
- learning algorithm
- online learning
- learning tasks
- mobile learning
- automatic transcription
- data sets
- learning systems
- unsupervised learning
- image processing
- image enhancement
- vector quantization
- automatic speech recognition
- speaker identification
- supervised learning
- previously learned
- synthesized speech