# Ordered and Binary Speaker Embedding

arXiv: https://arxiv.org/abs/2305.16043 · HTML: https://mlsanity.com/paper/2305.16043/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 33 references that are in the map.
- First posted on arXiv 25 May 2023.

## Builds on (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Deep Learning and the Information Bottleneck Principle](https://mlsanity.com/paper/1503.02406/) (2015)
- [Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks](https://mlsanity.com/paper/1810.09536/) (2018)
- [Learning Ordered Representations with Nested Dropout](https://mlsanity.com/paper/1402.0915/) (2014)
- [Exploring the Encoding Layer and Loss Function in End-to-End Speaker and Language Recognition System](https://mlsanity.com/paper/1804.05160/) (2018)
- [VoxSRC 2020: The Second VoxCeleb Speaker Recognition Challenge](https://mlsanity.com/paper/2012.06867/) (2020)
- [CN-Celeb: multi-genre speaker recognition](https://mlsanity.com/paper/2012.12468/) (2020)
- [Progressive Neural Image Compression with Nested Quantization and Latent Ordering](https://mlsanity.com/paper/2102.02913/) (2021)
- [Anytime Sampling for Autoregressive Models via Ordered Autoencoding](https://mlsanity.com/paper/2102.11495/) (2021)
- [VoxSRC 2021: The Third VoxCeleb Speaker Recognition Challenge](https://mlsanity.com/paper/2201.04583/) (2022)
- [The 2021 NIST Speaker Recognition Evaluation](https://mlsanity.com/paper/2204.10242/) (2022)
- [A PCA-like Autoencoder](https://mlsanity.com/paper/1904.01277/) (2019)
- [Deep Speaker Feature Learning for Text-independent Speaker Verification](https://mlsanity.com/paper/1705.03670/) (2017)
- [Binary Speaker Embedding](https://mlsanity.com/paper/1510.05937/) (2015)

## Abstract (arXiv)

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.