End-to-end Music-mixed Speech Recognition.
Jeongwoo WooMasato MimuraKazuyoshi YoshiiTatsuya KawaharaPublished in: APSIPA (2020)
Keyphrases
- end to end
- speech recognition
- hidden markov models
- language model
- speech signal
- speech processing
- speech recognizer
- speech synthesis
- automatic speech recognition
- speech recognition technology
- speech recognition systems
- speaker identification
- pattern recognition
- congestion control
- noisy environments
- speaker independent
- speaker adaptation
- speaker dependent
- music information retrieval
- neural network
- feature extraction
- image processing