Incorporating Uncertainty from Speaker Embedding Estimation to Speaker Verification

Qiongqiong Wang, Kong Aik Lee, Tianchi Liu

Research output: Journal article publicationConference articleAcademic researchpeer-review

3 Citations (Scopus)

Abstract

Speech utterances recorded under differing conditions exhibit varying degrees of confidence in their embedding estimates, i.e., uncertainty, even if they are extracted using the same neural network. This paper aims to incorporate the uncertainty estimate produced in the xi-vector network front-end with a probabilistic linear discriminant analysis (PLDA) back-end scoring for speaker verification. To achieve this we derive a posterior covariance matrix, which measures the uncertainty, from the frame-wise precisions to the embedding space. We propose a log-likelihood ratio function for the PLDA scoring with the uncertainty propagation. We also propose to replace the length normalization pre-processing technique with a length scaling technique for the application of uncertainty propagation in the back-end. Experimental results on the VoxCeleb-1, SITW test sets as well as a domain-mismatched CNCeleb1-E set show the effectiveness of the proposed techniques with 14.5%-41.3% EER reductions and 4.6%-25.3% minDCF reductions.

Original languageEnglish
Article number193814
JournalICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
DOIs
Publication statusPublished - Jun 2023
Externally publishedYes
Event48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023 - Rhodes Island, Greece
Duration: 4 Jun 202310 Jun 2023

Keywords

  • PLDA
  • speaker embeddings
  • speaker verification
  • uncertainty
  • xi-vector

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Incorporating Uncertainty from Speaker Embedding Estimation to Speaker Verification'. Together they form a unique fingerprint.

Cite this