IEICE Electronics Express | |
Linear-scale perceptual feature extraction for Speech Bandwidth Extensions | |
Koeng-Mo Sung1  Kuekjae Lee1  Sang Bae Chon1  Mingu Lee1  | |
[1] Applied Acoustics Lab., Institute of New Media and Communications, Department of Electrical Engineering, Seoul National University | |
关键词: BWE; NMF; MFCCs; | |
DOI : 10.1587/elex.8.1143 | |
学科分类:电子、光学、磁材料 | |
来源: Denshi Jouhou Tsuushin Gakkai | |
【 摘 要 】
References(6)This paper presents a new method to extract linear-scale perceptual feature as a subsitute of MFCCs for highband (3.4kHz∼) in Speech Bandwidth Extensions(BWE). The feature extraction method is based on the mel-scale constrained Nonnegative Matrix Factorization(NMF), which decompose linear-scale log spectrum into a linear combination of mel-scale latent variables. While MFCCs parametrization contains non-invertible procedures, suggested feature is represented in linear-scale and proper to recover the highband time-domain speech. Experiment results report that suggested feature shows better instrumental performance with narrowband MFCCs than real cepstrum without additional computation.
【 授权许可】
Unknown
【 预 览 】
Files | Size | Format | View |
---|---|---|---|
RO201911300115525ZK.pdf | 604KB | download |