# On deep speaker embeddings for text-independent speaker recognition

arXiv: https://arxiv.org/abs/1804.10080 · HTML: https://mlsanity.com/paper/1804.10080/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Apr 2018.

## Built on by (most cited first, 6 of 6)

- [STC speaker recognition systems for the NIST SRE 2021](https://mlsanity.com/paper/2111.02298/) (2021)
- [Robust Speaker Recognition with Transformers Using wav2vec 2.0](https://mlsanity.com/paper/2203.15095/) (2022)
- [Serialized Multi-Layer Multi-Head Attention for Neural Speaker Embedding](https://mlsanity.com/paper/2107.06493/) (2021)
- [Universal speaker recognition encoders for different speech segments duration](https://mlsanity.com/paper/2210.16231/) (2022)
- [DS-TDNN: Dual-stream Time-delay Neural Network with Global-aware Filter for Speaker Verification](https://mlsanity.com/paper/2303.11020/) (2023)
- [Investigation of Different Calibration Methods for Deep Speaker Embedding based Verification Systems](https://mlsanity.com/paper/2203.15106/) (2022)

## Abstract (arXiv)

We investigate deep neural network performance in the textindependent speaker recognition task. We demonstrate that using angular softmax activation at the last classification layer of a classification neural network instead of a simple softmax activation allows to train a more generalized discriminative speaker embedding extractor. Cosine similarity is an effective metric for speaker verification in this embedding space. We also address the problem of choosing an architecture for the extractor. We found that deep networks with residual frame level connections outperform wide but relatively shallow architectures. This paper also proposes several improvements for previous DNN-based extractor systems to increase the speaker recognition accuracy. We show that the discriminatively trained similarity metric learning approach outperforms the standard LDA-PLDA method as an embedding backend. The results obtained on Speakers in the Wild and NIST SRE 2016 evaluation sets demonstrate robustness of the proposed systems when dealing with close to real-life conditions.