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