End-to-End Multi-Speaker Speech Recognition using Speaker Embeddings and Transfer Learning.
Pavel DenisovNgoc Thang VuPublished in: CoRR (2019)
Keyphrases
- end to end
- transfer learning
- speech recognition
- speaker recognition
- audio visual
- automatic speech recognition
- speaker verification
- speaker identification
- speaker diarization
- knowledge transfer
- learning tasks
- labeled data
- cross domain
- speech signal
- semi supervised learning
- active learning
- reinforcement learning
- collaborative filtering
- transfer knowledge
- multi task
- text classification
- manifold alignment
- learning algorithm
- application layer
- congestion control
- machine learning
- domain adaptation
- target domain
- language model
- data sets
- machine learning algorithms
- text categorization
- unlabeled data
- dimensionality reduction
- semi supervised
- decision trees
- cross domain learning
- text localization and recognition