Acoustic Data-Driven Subword Modeling for End-to-End Speech Recognition.
Wei ZhouMohammad ZeineldeenZuoyun ZhengRalf SchlüterHermann NeyPublished in: CoRR (2021)
Keyphrases
- speech recognition
- end to end
- data driven
- speech recognition systems
- speech recognizers
- speaker independent
- language model
- speech recognizer
- acoustic models
- speech signal
- hidden markov models
- pattern recognition
- automatic speech recognition
- speech processing
- congestion control
- noisy speech
- speech synthesis
- speech recognition technology
- speaker identification
- speaker diarization
- noisy environments
- multimedia
- speaker recognition
- neural network
- probabilistic model
- bayesian networks