Estimation of spectral subtraction parameter-set for maximizing speech recognition performance.
Shintaro KuboRyoichi MiyazakiPublished in: GCCE (2016)
Keyphrases
- speech recognition
- spectral subtraction
- parameter set
- speech signal
- noisy speech
- hidden markov models
- language model
- speech synthesis
- automatic speech recognition
- pattern recognition
- noisy environments
- speech recognition systems
- speech recognizer
- vocal tract
- speaker identification
- parameter settings
- linear prediction
- feature extraction
- background noise
- neural network
- frequency domain
- computer vision