# Probing the Information Encoded in X-vectors

arXiv: https://arxiv.org/abs/1909.06351 · HTML: https://mlsanity.com/paper/1909.06351/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Sep 2019.

## Built on by (most cited first, 18 of 18)

- [What all do audio transformer models hear? Probing Acoustic Representations for Language Delivery and its Structure](https://mlsanity.com/paper/2101.00387/) (2021)
- [VoxCeleb Enrichment for Age and Gender Recognition](https://mlsanity.com/paper/2109.13510/) (2021)
- [Are disentangled representations all you need to build speaker anonymization systems?](https://mlsanity.com/paper/2208.10497/) (2022)
- [Data Quality as Predictor of Voice Anti-Spoofing Generalization](https://mlsanity.com/paper/2103.14602/) (2021)
- [Layer-wise Minimal Pair Probing Reveals Contextual Grammatical-Conceptual Hierarchy in Speech Representations](https://mlsanity.com/paper/2509.15655/) (2025)
- [Causal Tracing of Audio-Text Fusion in Large Audio Language Models](https://mlsanity.com/paper/2603.13768/) (2026)
- [Classification of Emotions and Evaluation of Customer Satisfaction from Speech in Real World Acoustic Environments](https://mlsanity.com/paper/2108.11981/) (2021)
- [LASPA: Language Agnostic Speaker Disentanglement with Prefix-Tuned Cross-Attention](https://mlsanity.com/paper/2506.02083/) (2025)
- [The Impact of Automatic Speech Transcription on Speaker Attribution](https://mlsanity.com/paper/2507.08660/) (2025)
- [Causally Disentangled Contrastive Learning for Multilingual Speaker Embeddings](https://mlsanity.com/paper/2602.01363/) (2026)
- [On the Impact of Voice Anonymization on Speech Diagnostic Applications: a Case Study on COVID-19 Detection](https://mlsanity.com/paper/2304.02181/) (2023)
- [Probing the Information Encoded in Neural-based Acoustic Models of Automatic Speech Recognition Systems](https://mlsanity.com/paper/2402.19443/) (2024)
- [Discrete Unit based Masking for Improving Disentanglement in Voice Conversion](https://mlsanity.com/paper/2409.11560/) (2024)
- [Probing Low-Level Acoustic Attribute Encoding in CLAP Audio Embeddings](https://mlsanity.com/paper/2607.03806/) (2026)
- [Domain-Dependent Speaker Diarization for the Third DIHARD Challenge](https://mlsanity.com/paper/2101.09884/) (2021)
- [An analysis on the effects of speaker embedding choice in non auto-regressive TTS](https://mlsanity.com/paper/2307.09898/) (2023)
- [Leveraging Speaker Embeddings in End-to-End Neural Diarization for Two-Speaker Scenarios](https://mlsanity.com/paper/2407.01317/) (2024)
- [The Voiceprint Fallacy: Why Voices Are Not Unique Biometric Imprints](https://mlsanity.com/paper/2608.07980/) (2026)

## Abstract (arXiv)

Deep neural network based speaker embeddings, such as x-vectors, have been shown to perform well in text-independent speaker recognition/verification tasks. In this paper, we use simple classifiers to investigate the contents encoded by x-vector embeddings. We probe these embeddings for information related to the speaker, channel, transcription (sentence, words, phones), and meta information about the utterance (duration and augmentation type), and compare these with the information encoded by i-vectors across a varying number of dimensions. We also study the effect of data augmentation during extractor training on the information captured by x-vectors. Experiments on the RedDots data set show that x-vectors capture spoken content and channel-related information, while performing well on speaker verification tasks.