English

Optimized Power Normalized Cepstral Coefficients towards Robust Deep Speaker Verification

Sound 2021-09-27 v1 Artificial Intelligence Audio and Speech Processing

Abstract

After their introduction to robust speech recognition, power normalized cepstral coefficient (PNCC) features were successfully adopted to other tasks, including speaker verification. However, as a feature extractor with long-term operations on the power spectrogram, its temporal processing and amplitude scaling steps dedicated on environmental compensation may be redundant. Further, they might suppress intrinsic speaker variations that are useful for speaker verification based on deep neural networks (DNN). Therefore, in this study, we revisit and optimize PNCCs by ablating its medium-time processor and by introducing channel energy normalization. Experimental results with a DNN-based speaker verification system indicate substantial improvement over baseline PNCCs on both in-domain and cross-domain scenarios, reflected by relatively 5.8% and 61.2% maximum lower equal error rate on VoxCeleb1 and VoxMovies, respectively.

Keywords

Cite

@article{arxiv.2109.12058,
  title  = {Optimized Power Normalized Cepstral Coefficients towards Robust Deep Speaker Verification},
  author = {Xuechen Liu and Md Sahidullah and Tomi Kinnunen},
  journal= {arXiv preprint arXiv:2109.12058},
  year   = {2021}
}

Comments

Accepted for publication at ASRU 2021

R2 v1 2026-06-24T06:18:10.797Z