# A Unified Deep Neural Network for Speaker and Language Recognition

arXiv: https://arxiv.org/abs/1504.00923 · HTML: https://mlsanity.com/paper/1504.00923/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Apr 2015.

## Built on by (most cited first, 2 of 2)

- [Benchmarking Filtered Approximate Nearest Neighbor Search Algorithms on Transformer-based Embedding Vectors](https://mlsanity.com/paper/2507.21989/) (2025)
- [Curricular SincNet: Towards Robust Deep Speaker Recognition by Emphasizing Hard Samples in Latent Space](https://mlsanity.com/paper/2108.10714/) (2021)

## Abstract (arXiv)

Learned feature representations and sub-phoneme posteriors from Deep Neural Networks (DNNs) have been used separately to produce significant performance gains for speaker and language recognition tasks. In this work we show how these gains are possible using a single DNN for both speaker and language recognition. The unified DNN approach is shown to yield substantial performance improvements on the the 2013 Domain Adaptation Challenge speaker recognition task (55% reduction in EER for the out-of-domain condition) and on the NIST 2011 Language Recognition Evaluation (48% reduction in EER for the 30s test condition).