Deep factorization for speech signal.
Lantian LiDong WangYixiang ChenYing ShiZhiyuan TangThomas Fang ZhengPublished in: CoRR (2018)
Keyphrases
- speech signal
- speech recognition
- automatic speech recognition
- background noise
- vocal tract
- linear prediction
- non stationary
- automatic speech recognition systems
- noisy environments
- speaker identification
- speech enhancement
- hidden markov models
- spectral analysis
- speaker recognition
- hearing aids
- matrix factorization
- acoustic features
- neural network
- cepstral coefficients
- speech quality
- fundamental frequency
- mel frequency cepstral coefficients
- information retrieval
- multiresolution
- probabilistic model