Latent space representation for multi-target speaker detection and identification with a sparse dataset using Triplet neural networks

TL;DR

This paper introduces a Triplet Neural Network approach to speaker recognition that outperforms traditional methods, especially on small datasets with limited samples per speaker, by effectively learning a discriminative latent space.

Contribution

The paper demonstrates that Triplet Neural Networks can significantly improve speaker recognition accuracy on small datasets compared to baseline models.

Findings

Outperforms baseline by 23% on the MCE 2018 dataset.

Reduces confusions by 46% in low-data scenarios.

Effective in small-sample speaker recognition tasks.

Abstract

We present an approach to tackle the speaker recognition problem using Triplet Neural Networks. Currently, the $i$-vector representation with probabilistic linear discriminant analysis (PLDA) is the most commonly used technique to solve this problem, due to high classification accuracy with a relatively short computation time. In this paper, we explore a neural network approach, namely Triplet Neural Networks (TNNs), to built a latent space for different classifiers to solve the Multi-Target Speaker Detection and Identification Challenge Evaluation 2018 (MCE 2018) dataset. This training set contains $i$-vectors from 3,631 speakers, with only 3 samples for each speaker, thus making speaker recognition a challenging task. When using the train and development set for training both the TNN and baseline model (i.e., similarity evaluation directly on the $i$-vector representation), our proposed model outperforms the baseline by 23%. When reducing the training data to only using the train set, our method results in 309 confusions for the Multi-target speaker identification task, which is 46% better than the baseline model. These results show that the representational power of TNNs is especially evident when training on small datasets with few instances available per class.