G2G: TTS-Driven Pronunciation Learning for Graphemic Hybrid ASR.
Duc LeThilo KöhlerChristian FuegenMichael L. SeltzerPublished in: ICASSP (2020)
Keyphrases
- speech recognition
- learning systems
- hybrid learning
- unsupervised learning
- reinforcement learning
- learning algorithm
- learning scheme
- learning process
- data sets
- language learning
- learning scenarios
- hidden markov models
- knowledge acquisition
- bayesian networks
- background knowledge
- mobile learning
- learning problems
- incremental learning
- information retrieval