Federated Acoustic Modeling For Automatic Speech Recognition.
Xiaodong CuiSongtao LuBrian KingsburyPublished in: CoRR (2021)
Keyphrases
- automatic speech recognition
- acoustic features
- speech recognition
- speech sounds
- speech recognizers
- hidden markov models
- speech segments
- speech signal
- word error rate
- broadcast news
- speech recognition systems
- formant frequencies
- acoustic models
- conversational speech
- spontaneous speech
- word recognition
- multiscale
- feature extraction
- machine learning
- maximum likelihood
- compound words
- speech retrieval
- neural network