Ordered and Binary Speaker Embedding
Sound
2023-05-26 v1 Machine Learning
Audio and Speech Processing
Abstract
Modern speaker recognition systems represent utterances by embedding vectors. Conventional embedding vectors are dense and non-structural. In this paper, we propose an ordered binary embedding approach that sorts the dimensions of the embedding vector via a nested dropout and converts the sorted vectors to binary codes via Bernoulli sampling. The resultant ordered binary codes offer some important merits such as hierarchical clustering, reduced memory usage, and fast retrieval. These merits were empirically verified by comprehensive experiments on a speaker identification task with the VoxCeleb and CN-Celeb datasets.
Cite
@article{arxiv.2305.16043,
title = {Ordered and Binary Speaker Embedding},
author = {Jiaying Wang and Xianglong Wang and Namin Wang and Lantian Li and Dong Wang},
journal= {arXiv preprint arXiv:2305.16043},
year = {2023}
}
Comments
to be published in INTERSPEECH 2023