Graph Neural Network Backend for Speaker Recognition

Currently, most speaker recognition backends, such as cosine, linear discriminant analysis (LDA), or probabilistic linear discriminant analysis (PLDA), make decisions by calculating similarity or distance between enrollment and test embeddings which are already extracted from neural networks. Howeve...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors He, Liang, Li, Ruida, Niu, Mengqi
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 17.08.2023
Subjects
Decision analysis
Discriminant analysis
Graph neural networks
Graph theory
Message passing
Neural networks
Similarity
Speech recognition
Trigonometric functions
Online AccessGet full text

Cover

More Information
Summary:Currently, most speaker recognition backends, such as cosine, linear discriminant analysis (LDA), or probabilistic linear discriminant analysis (PLDA), make decisions by calculating similarity or distance between enrollment and test embeddings which are already extracted from neural networks. However, for each embedding, the local structure of itself and its neighbor embeddings in the low-dimensional space is different, which may be helpful for the recognition but is often ignored. In order to take advantage of it, we propose a graph neural network (GNN) backend to mine latent relationships among embeddings for classification. We assume all the embeddings as nodes on a graph, and their edges are computed based on some similarity function, such as cosine, LDA+cosine, or LDA+PLDA. We study different graph settings and explore variants of GNN to find a better message passing and aggregation way to accomplish the recognition task. Experimental results on NIST SRE14 i-vector challenging, VoxCeleb1-O, VoxCeleb1-E, and VoxCeleb1-H datasets demonstrate that our proposed GNN backends significantly outperform current mainstream methods.
ISSN:2331-8422