Federated Acoustic Modeling for Automatic Speech Recognition.
Xiaodong CuiSongtao LuBrian KingsburyPublished in: ICASSP (2021)
Keyphrases
- automatic speech recognition
- speech recognition
- acoustic features
- speech sounds
- speech signal
- hidden markov models
- speech recognizers
- speech segments
- conversational speech
- speech recognition systems
- broadcast news
- digital libraries
- acoustic models
- speech retrieval
- recognition errors
- neural network
- noisy environments
- information retrieval
- word error rate
- speaker independent
- computer vision
- speech corpus
- image processing
- multi modal