# Factorization of Discriminatively Trained i-vector Extractor for Speaker Recognition

## TL;DR

This paper presents a factorized, compact discriminatively trained i-vector extractor that maintains performance while reducing complexity, leading to improved speaker verification results across diverse benchmarks.

## Contribution

It introduces a parameter-efficient, factorized model of the i-vector extractor optimized for discriminative training, enhancing speaker verification performance.

## Key findings

- Similar performance to original models with fewer parameters
- Discriminative training improves verification accuracy
- Effective across multiple acoustic domains

## Abstract

In this work, we continue in our research on i-vector extractor for speaker verification (SV) and we optimize its architecture for fast and effective discriminative training. We were motivated by computational and memory requirements caused by the large number of parameters of the original generative i-vector model. Our aim is to preserve the power of the original generative model, and at the same time focus the model towards extraction of speaker-related information. We show that it is possible to represent a standard generative i-vector extractor by a model with significantly less parameters and obtain similar performance on SV tasks. We can further refine this compact model by discriminative training and obtain i-vectors that lead to better performance on various SV benchmarks representing different acoustic domains.