A comparison between deep neural nets and kernel acoustic models for speech recognition.
Zhiyun LuDong GuoAlireza Bagheri GarakaniKuan LiuAvner MayAurélien BelletLinxi FanMichael CollinsBrian KingsburyMichael PichenyFei ShaPublished in: ICASSP (2016)
Keyphrases
- speech recognition
- neural nets
- acoustic models
- speech recognizer
- speaker independent
- automatic speech recognition
- feed forward
- neural network
- hidden markov models
- language model
- back propagation
- speech signal
- pattern recognition
- artificial neural networks
- speaker identification
- speech recognition systems
- kernel function
- noisy environments
- support vector
- kernel methods
- speaker diarization
- multimedia