Large-Scale Mixed-Bandwidth Deep Neural Network Acoustic Modeling for Automatic Speech Recognition.
Khoi-Nguyen C. MacXiaodong CuiWei ZhangMichael PichenyPublished in: INTERSPEECH (2019)
Keyphrases
- automatic speech recognition
- neural network
- acoustic features
- speech recognition
- speech sounds
- speech signal
- speech recognizers
- hidden markov models
- broadcast news
- speech segments
- speech retrieval
- recognition errors
- conversational speech
- spoken words
- speech corpus
- multiscale
- acoustic models
- noisy environments
- formant frequencies
- word error rate
- spontaneous speech
- multi modal
- language model
- probabilistic model
- information retrieval