# DELULU: Discriminative Embedding Learning Using Latent Units for Speaker-Aware Self-Trained Speech Foundational Model

arXiv: https://arxiv.org/abs/2510.17662 · HTML: https://mlsanity.com/paper/2510.17662/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 34 references that are in the map.
- First posted on arXiv 20 Oct 2025.

## Builds on (most cited first, 21 of 21)

- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [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)
- [Scaling Speech Technology to 1,000+ Languages](https://mlsanity.com/paper/2305.13516/) (2023)
- [Additive Margin Softmax for Face Verification](https://mlsanity.com/paper/1801.05599/) (2018)
- [YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone](https://mlsanity.com/paper/2112.02418/) (2021)
- [Dynamic-SUPERB: Towards A Dynamic, Collaborative, and Comprehensive Instruction-Tuning Benchmark for Speech](https://mlsanity.com/paper/2309.09510/) (2023)
- [EARS: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberation](https://mlsanity.com/paper/2406.06185/) (2024)
- [Speech SIMCLR: Combining Contrastive and Reconstruction Objective for Self-supervised Speech Representation Learning](https://mlsanity.com/paper/2010.13991/) (2020)
- [Reshape Dimensions Network for Speaker Recognition](https://mlsanity.com/paper/2407.18223/) (2024)
- [VoxBlink2: A 100K+ Speaker Recognition Corpus and the Open-Set Speaker-Identification Benchmark](https://mlsanity.com/paper/2407.11510/) (2024)
- [What Do Self-Supervised Speech and Speaker Models Learn? New Findings From a Cross Model Layer-Wise Analysis](https://mlsanity.com/paper/2401.17632/) (2024)
- [What Do Speech Foundation Models Not Learn About Speech?](https://mlsanity.com/paper/2410.12948/) (2024)
- [SVeritas: Benchmark for Robust Speaker Verification under Diverse Conditions](https://mlsanity.com/paper/2509.17091/) (2025)
- [CoLMbo: Speaker Language Model for Descriptive Profiling](https://mlsanity.com/paper/2506.09375/) (2025)
- [PDAF: A Phonetic Debiasing Attention Framework For Speaker Verification](https://mlsanity.com/paper/2409.05799/) (2024)
- [Self-Supervised Frameworks for Speaker Verification via Bootstrapped Positive Sampling](https://mlsanity.com/paper/2501.17772/) (2025)
- [CAARMA: Class Augmentation with Adversarial Mixup Regularization](https://mlsanity.com/paper/2503.16718/) (2025)

## Built on by (most cited first, 1 of 1)

- [What and When to Learn: CURriculum Ranking Loss for Large-Scale Speaker Verification](https://mlsanity.com/paper/2603.24432/) (2026)

## Abstract (arXiv)

Self-supervised speech models have achieved remarkable success on content-driven tasks, yet they remain limited in capturing speaker-discriminative features critical for verification, diarization, and profiling applications. We introduce textscDELULU, a speaker-aware self-trained foundational model that addresses this limitation by incorporating speaker-informed structure into pseudo-label generation. DELULU leverages frame-level embeddings from ReDimNet, a state-of-the-art speaker verification model, to guide k-means clustering during pre-training, introducing a speaker-discriminative inductive bias that aligns representation learning with speaker identity. DELULU significantly outperforms prior SSL models across a range of speaker-centric tasks, achieving up to 62% relative improvement in equal error rate (EER) for speaker verification and consistent gains on zero-shot profiling tasks including gender, age, accent, and speaker counting; notably surpassing even its teacher model on zero-shot evaluations. Our findings demonstrate that DELULU is a strong universal encoder for speaker-aware speech processing, enabling superior performance without task-specific fine-tuning.