.png){kind=icon}
.png){kind=icon}
Return
Optimizing Multi-Taper Features for Deep Speaker Verification
.png){kind=icon}
OA
AI
DOI：10.1109/LSP.2021.3122796.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Multi-taper estimators provide low-variance power spectrum estimates that can be used in place of the windowed discrete Fourier transform (DFT) to extract speech features such as mel-frequency cepstral coefficients (MFCCs). Even if past work has reported promising automatic speaker verification (ASV) results with Gaussian mixture model-based classifiers, the performance of multi-taper MFCCs with deep ASV systems remains an open question. Instead of a static-taper design, we propose to optimize the multi-taper estimator jointly with a deep neural network trained for ASV tasks. With a maximum improvement on the SITW corpus of 25.8% in terms of equal error rate over the static-taper, our method helps preserve a balanced level of leakage and variance, providing more robustness.
Keywords:
Feature extraction
Discrete Fourier transforms
Task analysis
Neural networks
Mel frequency cepstral coefficient
Stochastic processes
Standards
Multi-taper spectrum
speaker verification
Journal
IF:
9.6
Papers:
1.1W
Citations:
1.7W