Optimized Power Normalized Cepstral Coefficients Towards Robust Deep Speaker Verification - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Optimized Power Normalized Cepstral Coefficients Towards Robust Deep Speaker Verification

Résumé

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 mediumtime 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.
Fichier principal
Vignette du fichier
asru_1228.pdf (1.91 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03359173 , version 1 (30-09-2021)

Identifiants

  • HAL Id : hal-03359173 , version 1

Citer

Xuechen Liu, Md Sahidullah, Tomi Kinnunen. Optimized Power Normalized Cepstral Coefficients Towards Robust Deep Speaker Verification. ASRU 2021 - IEEE Automatic Speech Recognition and Understanding Workshop, Dec 2021, Cartagena, Colombia. ⟨hal-03359173⟩
32 Consultations
105 Téléchargements

Partager

Gmail Facebook X LinkedIn More