Sep 24, 2021 · In this study, we revisit and optimize PNCCs by ablating its medium-time processor and by introducing channel energy normalization.

Sep 30, 2021 · To the best of our knowledge, this is the first work on introducing and optimizing PNCCs for speaker verification systems using deep speaker ...

This study revisits and optimize power normalized cepstral coefficient features by ablating its medium-time processor and by introducing channel energy ...

Further, they might suppress intrinsic speaker variations that are useful for speaker verification based on deep neural networks (DNN). Therefore, in this study ...

Optimized Power Normalized Cepstral Coefficients Towards Robust Deep Speaker Verification. Year of publication. 2021. Authors.

The results of this study showed improved achievement over MFCC when power normalized cepstral coefficients (PNCC) and multitapper were used in wild conditions.

Sep 24, 2021 · Further, they might suppress intrinsic speaker variations that are useful for speaker verification based on deep neural networks (DNN).

Experimental results with a DNN-based speaker verification system indicate substantial improvement over baseline PNCCs on both in-domain and cross-domain ...

We propose a learnable mel-frequency cepstral coefficient (MFCC) frontend architecture for deep neural network (DNN) based automatic speaker verification.

We propose a learnable mel-frequency cepstral coefficient (MFCC) frontend architecture for deep neural network (DNN) based automatic speaker verification.