Multi-Head State Space Model for Speech Recognition.
Yassir FathullahChunyang WuYuan ShangguanJunteng JiaWenhan XiongJay MahadeokarChunxi LiuYangyang ShiOzlem KalinliMike SeltzerMark J. F. GalesPublished in: CoRR (2023)
Keyphrases
- speech recognition
- state space model
- hidden markov models
- state estimation
- speech signal
- language model
- speech processing
- speech synthesis
- speech recognizer
- automatic speech recognition
- pattern recognition
- kalman filtering
- speech recognition technology
- autoregressive
- kalman filter
- speech recognition systems
- speaker identification
- image processing
- noisy environments
- additive noise
- speaker independent
- machine learning
- speaker dependent