Scaling sparsemax based channel selection for speech recognition with ad-hoc microphone arrays.
Junqi ChenXiao-Lei ZhangPublished in: CoRR (2021)
Keyphrases
- speech recognition
- automatic speech recognition
- speaker diarization
- hidden markov models
- language model
- speech processing
- speech recognizer
- speech recognition technology
- speech signal
- speech synthesis
- pattern recognition
- speech understanding
- speech recognition systems
- speech recognizers
- noisy environments
- visual information
- keyword spotting
- speaker independent
- speaker dependent
- speech retrieval
- neural network
- broadcast news
- multi modal
- probabilistic model
- speaker adaptation
- image processing