Open AccessSpeech Magnitude Spectrum Reconstruction from MFCCs Using Deep Neural Network
Author(s) -
Jiang Wenbin,
Liu Peilin,
Wen Fei
Publication year - 2018
Publication title -
chinese journal of electronics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.267
H-Index - 25
eISSN - 2075-5597
pISSN - 1022-4653
DOI - 10.1049/cje.2017.09.018
Subject(s) - mel frequency cepstrum , timit , computer science , speech recognition , artificial neural network , cepstrum , magnitude (astronomy) , spectrum (functional analysis) , pattern recognition (psychology) , artificial intelligence , inference , deep neural networks , hidden markov model , feature extraction , physics , quantum mechanics , astronomy
This work proposes a Deep neural network (DNN) based method for reconstructing speech magnitude spectrum from Mel‐frequency cepstral coefficients (MFCCs). We train a DNN using MFCC vectors as input and the corresponding speech magnitude spectrum as desired output. Exploiting the strong inference power of DNN, the proposed method has the capability to accurately estimate the speech magnitude spectrum even from truncated MFCC vectors. Experiments on TIMIT corpus demonstrate that the proposed method achieves significantly better performance compared with traditional methods.