Analyzing Speaker Verification Embedding Extractors And Back-ends Under Language And Channel Mismatch

Abstract

In this paper, we analyze the behavior and performance of speaker embeddings and the back-end scoring model under domain and language mismatch. We present our findings regarding ResNet-based speaker embedding architectures and show that reduced temporal stride yields improved performance. We then consider a PLDA back-end and show how a combination of small speaker subspace, language-dependent PLDA mixture, and nuisance-attribute projection can have a drastic impact on the performance of the system. Besides, we present an efficient way of scoring and fusing class posterior logit vectors recently shown to perform well for speaker verification task. The experiments are performed using the NIST SRE 2021 setup.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keysilnova2022analyzing

Related papers

• Adapting End-to-end Neural Speaker Verification To New Languages And Recording Conditions With Adversarial Training (2018)9.59
• Squeezing Value Of Cross-domain Labels: A Decoupled Scoring Approach For Speaker Verification (2020)0.00
• NPU Speaker Verification System For INTERSPEECH 2020 Far-field Speaker Verification Challenge (2020)7.50
• Generative Adversarial Speaker Embedding Networks For Domain Robust End-to-end Speaker Verification (2018)0.00
• Domain Adaptation Based Speaker Recognition On Short Utterances (2016)0.00
• Speaker Verification Using End-to-end Adversarial Language Adaptation (2018)11.19
• Scoring Of Large-margin Embeddings For Speaker Verification: Cosine Or PLDA? (2022)9.76
• Deep Speaker Embeddings For Far-field Speaker Recognition On Short Utterances (2020)11.29