Closed-set speaker identification system based on MFCC and PNCC features combination with different fusion strategies

Musab T.S. Al-Kaltakchi, Mohammed A.M. Abdullah, Wai L. Woo, Satnam S. Dlay

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

4 Citations (Scopus)

Abstract

In this chapter, we investigate novel fusion strategies for text-independent speaker identification. In this context, we present four main simulations for speaker identification accuracy (SIA) including different fusion strategies such as feature-based early fusion, score-based late fusion, early-late fusion (combination of feature- and score-based), late fusion for concatenated features, and statistically independent normalized scores fusion for all the previous scores. The Gaussian mixture model (GMM) with the universal background model (UBM) is used for voice modeling. For the original clean speech recording, Mel frequency cepstral coefficient (MFCC) features are utilized. power normalized cepstral coefficient (PNCC) features are employed in the noisy environment due to their efficiency with noise. Hence, to produce a robust speaker identification system, the MFCCs and PNCCs are combined. In addition, cepstral mean and variance normalization (CMVN) and feature warping (FW) are used in order to mitigate possible linear channel effects, as they are robust for channel and handset mismatch and additive noise. We used the TIMIT database to evaluate the closed-set speaker identification. Results show the highest SIA (95%) at a mixture size of 512 using the late fusion approach. Moreover, a fusion-based technique for MFCC and PNCC features results in better accuracy than using each feature alone.

Original languageEnglish
Title of host publicationApplied Speech Processing
Subtitle of host publicationAlgorithms and Case Studies
PublisherElsevier
Pages147-173
Number of pages27
ISBN (Print)9780128238981
DOIs
Publication statusPublished - 1 Jan 2021

Keywords

  • Gaussian mixture model
  • MFCC
  • PNCC
  • Speaker identification
  • Speaker models

Fingerprint

Dive into the research topics of 'Closed-set speaker identification system based on MFCC and PNCC features combination with different fusion strategies'. Together they form a unique fingerprint.

Cite this