Quantifying Noise Robustness of Bone-Conducted Speech.
Shiming ZhangYosuke SugiuraNozomiko YasuiTetsuya ShimamuraPublished in: MWSCAS (2020)
Keyphrases
- greater robustness
- noisy environments
- signal to noise ratio
- random noise
- speech recognition
- noise reduction
- speech enhancement
- speech signal
- noise level
- noise immunity
- additive noise
- noise model
- missing data
- endpoint detection
- noise sensitivity
- background noise
- salt pepper
- image transformations
- gaussian noise
- three dimensional
- text to speech
- speech synthesis
- automatic speech recognition
- image structure
- computational efficiency
- neural network