Improving End-to-End Automatic Speech Recognition with Multi-Layer-Enriched Supervised Learning.
Jingyu ZhaoRuwei LiWeidong AnPublished in: ICSPCC (2023)
Keyphrases
- end to end
- multi layer
- automatic speech recognition
- supervised learning
- speech recognition
- word error rate
- speech signal
- hidden markov models
- conversational speech
- neural nets
- neural network
- broadcast news
- congestion control
- unsupervised learning
- learning tasks
- speech retrieval
- reinforcement learning
- semi supervised learning
- training data
- cross layer
- learning algorithm
- machine learning
- semi supervised
- training set
- pattern recognition
- application layer
- multiscale
- genetic algorithm