On The Model Size Selection For Speaker Identification

TL;DR

This paper investigates how selecting different model sizes for each speaker can enhance speaker identification accuracy, proposing criteria and a new algorithm that outperform fixed-size models.

Contribution

It introduces a novel approach for speaker identification that optimizes model size per speaker, improving accuracy over traditional fixed-size models.

Findings

Variable model sizes improve identification rates.

Proposed criteria effectively select optimal model sizes.

New algorithm outperforms classical fixed-size systems.

Abstract

In this paper we evaluate the relevance of the model size for speaker identification. We show that it is possible to improve the identification rates if a different model size is used for each speaker. We also present some criteria for selecting the model size, and a new algorithm that outperforms the classical system with a fixed model size.