# Source -Free Domain Adaptation for Speaker Verification in Data-Scarce Languages and Noisy Channels

arXiv: https://arxiv.org/abs/2406.05863 · HTML: https://mlsanity.com/paper/2406.05863/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 30 references that are in the map.
- First posted on arXiv 9 Jun 2024.

## Builds on (most cited first, 11 of 11)

- [VoxCeleb2: Deep Speaker Recognition](https://mlsanity.com/paper/1806.05622/) (2018)
- [VoxCeleb: a large-scale speaker identification dataset](https://mlsanity.com/paper/1706.08612/) (2017)
- [ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification](https://mlsanity.com/paper/2005.07143/) (2020)
- [SpeechBrain: A General-Purpose Speech Toolkit](https://mlsanity.com/paper/2106.04624/) (2021)
- [Return of Frustratingly Easy Domain Adaptation](https://mlsanity.com/paper/1511.05547/) (2015)
- [A Brief Review of Domain Adaptation](https://mlsanity.com/paper/2010.03978/) (2020)
- [Attentive Statistics Pooling for Deep Speaker Embedding](https://mlsanity.com/paper/1803.10963/) (2018)
- [Domain Adaptation without Source Data](https://mlsanity.com/paper/2007.01524/) (2020)
- [The CORAL+ Algorithm for Unsupervised Domain Adaptation of PLDA](https://mlsanity.com/paper/1812.10260/) (2018)
- [Cross-lingual Text-independent Speaker Verification using Unsupervised Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1908.01447/) (2019)
- [VAE-based Domain Adaptation for Speaker Verification](https://mlsanity.com/paper/1908.10092/) (2019)

## Abstract (arXiv)

Domain adaptation is often hampered by exceedingly small target datasets and inaccessible source data. These conditions are prevalent in speech verification, where privacy policies and/or languages with scarce speech resources limit the availability of sufficient data. This paper explored techniques of sourcefree domain adaptation unto a limited target speech dataset for speaker verificationin data-scarce languages. Both language and channel mis-match between source and target were investigated. Fine-tuning methods were evaluated and compared across different sizes of labeled target data. A novel iterative cluster-learn algorithm was studied for unlabeled target datasets.