Missing component restoration for masked speech signals based on time-domain spectrogram factorization.
Shogo SekiHirokazu KameokaTomoki TodaKazuya TakedaPublished in: MLSP (2017)
Keyphrases
- speech signal
- speech recognition
- linear prediction
- automatic speech recognition
- noisy environments
- vocal tract
- background noise
- additive noise
- missing data
- spectral analysis
- matrix factorization
- non stationary
- image restoration
- automatic speech recognition systems
- speech enhancement
- blind source separation
- frequency domain
- hidden markov models
- image processing
- speech quality
- denoising
- fundamental frequency
- computer vision
- image acquisition
- noisy images