# Cross-Lingual Speaker Verification with Domain-Balanced Hard Prototype Mining and Language-Dependent Score Normalization

arXiv: https://arxiv.org/abs/2007.07689 · HTML: https://mlsanity.com/paper/2007.07689/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jul 2020.

## Built on by (most cited first, 5 of 5)

- [Example-based Explanations with Adversarial Attacks for Respiratory Sound Analysis](https://mlsanity.com/paper/2203.16141/) (2022)
- [SpeakerStew: Scaling to Many Languages with a Triaged Multilingual Text-Dependent and Text-Independent Speaker Verification System](https://mlsanity.com/paper/2104.02125/) (2021)
- [Enrollment-stage Backdoor Attacks on Speaker Recognition Systems via Adversarial Ultrasound](https://mlsanity.com/paper/2306.16022/) (2023)
- [POLY-SIM: Polyglot Speaker Identification with Missing Modality Grand Challenge 2026 Evaluation Plan](https://mlsanity.com/paper/2603.24569/) (2026)
- [L-Proto: Language-Aware Episodic Prototypical Training for Multilingual Speaker Verification](https://mlsanity.com/paper/2606.17416/) (2026)

## Abstract (arXiv)

In this paper we describe the top-scoring IDLab submission for the text-independent task of the Short-duration Speaker Verification (SdSV) Challenge 2020. The main difficulty of the challenge exists in the large degree of varying phonetic overlap between the potentially cross-lingual trials, along with the limited availability of in-domain DeepMine Farsi training data. We introduce domain-balanced hard prototype mining to fine-tune the state-of-the-art ECAPA-TDNN x-vector based speaker embedding extractor. The sample mining technique efficiently exploits speaker distances between the speaker prototypes of the popular AAM-softmax loss function to construct challenging training batches that are balanced on the domain-level. To enhance the scoring of cross-lingual trials, we propose a language-dependent s-norm score normalization. The imposter cohort only contains data from the Farsi target-domain which simulates the enrollment data always being Farsi. In case a Gaussian-Backend language model detects the test speaker embedding to contain English, a cross-language compensation offset determined on the AAM-softmax speaker prototypes is subtracted from the maximum expected imposter mean score. A fusion of five systems with minor topological tweaks resulted in a final MinDCF and EER of 0.065 and 1.45% respectively on the SdSVC evaluation set.