# S-vectors and TESA: Speaker Embeddings and a Speaker Authenticator Based on Transformer Encoder

arXiv: https://arxiv.org/abs/2008.04659 · HTML: https://mlsanity.com/paper/2008.04659/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Aug 2020.

## Built on by (most cited first, 8 of 8)

- [Non-Contrastive Self-supervised Learning for Utterance-Level Information Extraction from Speech](https://mlsanity.com/paper/2208.05445/) (2022)
- [Large-scale learning of generalised representations for speaker recognition](https://mlsanity.com/paper/2210.10985/) (2022)
- [Boosting keyword spotting through on-device learnable user speech characteristics](https://mlsanity.com/paper/2403.07802/) (2024)
- [DT-SV: A Transformer-based Time-domain Approach for Speaker Verification](https://mlsanity.com/paper/2205.13249/) (2022)
- [Improving Transformer-based Networks With Locality For Automatic Speaker Verification](https://mlsanity.com/paper/2302.08639/) (2023)
- [Speech Rhythm-Based Speaker Embeddings Extraction from Phonemes and Phoneme Duration for Multi-Speaker Speech Synthesis](https://mlsanity.com/paper/2402.07085/) (2024)
- [Parameter-Free Attentive Scoring for Speaker Verification](https://mlsanity.com/paper/2203.05642/) (2022)
- [UniPET-SPK: A Unified Framework for Parameter-Efficient Tuning of Pre-trained Speech Models for Robust Speaker Verification](https://mlsanity.com/paper/2501.16542/) (2025)

## Abstract (arXiv)

One of the most popular speaker embeddings is x-vectors, which are obtained from an architecture that gradually builds a larger temporal context with layers. In this paper, we propose to derive speaker embeddings from Transformer's encoder trained for speaker classification. Self-attention, on which Transformer's encoder is built, attends to all the features over the entire utterance and might be more suitable in capturing the speaker characteristics in an utterance. We refer to the speaker embeddings obtained from the proposed speaker classification model as s-vectors to emphasize that they are obtained from an architecture that heavily relies on self-attention. Through experiments, we demonstrate that s-vectors perform better than x-vectors. In addition to the s-vectors, we also propose a new architecture based on Transformer's encoder for speaker verification as a replacement for speaker verification based on conventional probabilistic linear discriminant analysis (PLDA). This architecture is inspired by the next sentence prediction task of bidirectional encoder representations from Transformers (BERT), and we feed the s-vectors of two utterances to verify whether they belong to the same speaker. We name this architecture the Transformer encoder speaker authenticator (TESA). Our experiments show that the performance of s-vectors with TESA is better than s-vectors with conventional PLDA-based speaker verification.