Text and Synthetic Data for Domain Adaptation in End-to-End Speech Recognition.
Juan HussainChristian HuberSebastian StükerAlexander H. WaibelPublished in: SPECOM (2021)
Keyphrases
- synthetic data
- end to end
- speech recognition
- domain adaptation
- hidden markov models
- multiple sources
- labeled data
- semi supervised
- cross domain
- pattern recognition
- text mining
- language model
- semi supervised learning
- real world
- data sets
- test data
- transfer learning
- information retrieval
- target domain
- sentiment classification
- database
- document classification
- multimedia
- neural network
- keywords
- unlabeled data
- image processing
- text classification
- text documents
- text data
- decision trees