Speech Enhancement Based on Masking Approach Considering Speech Quality and Acoustic Confidence for Noisy Speech Recognition.
Shih-Chuan ChuChung-Hsien WuYun-Wen LinPublished in: APSIPA ASC (2021)
Keyphrases
- speech signal
- speech recognition
- speech enhancement
- noisy environments
- noisy speech
- acoustic features
- speech recognition systems
- speaker independent
- background noise
- automatic speech recognition
- sound source
- speaker identification
- linear prediction
- language model
- mel frequency cepstral coefficients
- vocal tract
- hidden markov models
- adaptive filtering
- additive noise
- speech synthesis
- spectral analysis
- pattern recognition
- speaker recognition
- spectral subtraction
- neural network
- image sequences