Federated Acoustic Model Optimization for Automatic Speech Recognition.
Conghui TanDi JiangHuaxiao MoJinhua PengYongxin TongWeiwei ZhaoChaotao ChenRongzhong LianYuanfeng SongQian XuPublished in: DASFAA (3) (2020)
Keyphrases
- automatic speech recognition
- speech recognition
- speech signal
- hidden markov models
- speech retrieval
- noisy environments
- broadcast news
- word error rate
- conversational speech
- recognition errors
- word recognition
- acoustic features
- spoken words
- neural network
- image processing
- spontaneous speech
- multi modal
- speech corpus
- information retrieval systems