A Comparison of Label-Synchronous and Frame-Synchronous End-to-End Models for Speech Recognition.
Linhao DongCheng YiJianzong WangShiyu ZhouShuang XuXueli JiaBo XuPublished in: CoRR (2020)
Keyphrases
- end to end
- speech recognition
- hidden markov models
- speech signal
- acoustic models
- speech processing
- congestion control
- speech synthesis
- speaker identification
- language model
- speech recognition systems
- speech recognition technology
- automatic speech recognition
- pattern recognition
- speech recognizer
- isolated word
- multimedia
- speaker independent
- probabilistic model
- image sequences