Improved cepstra minimum-mean-square-error noise reduction algorithm for robust speech recognition.
Jinyu LiYan HuangYifan GongPublished in: ICASSP (2017)
Keyphrases
- speech recognition
- noisy environments
- minimum mean square error
- signal to noise ratio
- hidden markov models
- automatic speech recognition
- language model
- noisy speech
- speech signal
- noise reduction
- speaker identification
- recursive algorithm
- speech synthesis
- speech recognition technology
- speech enhancement
- speech recognizer
- speech recognition systems
- background noise
- pattern recognition
- speaker independent
- noise level
- neural network
- noise model
- probabilistic model