# NEST: Self-supervised Fast Conformer as All-purpose Seasoning to Speech Processing Tasks

arXiv: https://arxiv.org/abs/2408.13106 · HTML: https://mlsanity.com/paper/2408.13106/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Aug 2024.

## Built on by (most cited first, 3 of 3)

- [Sortformer: A Novel Approach for Permutation-Resolved Speaker Supervision in Speech-to-Text Systems](https://mlsanity.com/paper/2409.06656/) (2024)
- [BEST-RQ-Based Self-Supervised Learning for Whisper Domain Adaptation](https://mlsanity.com/paper/2510.24570/) (2025)
- [The Hidden Cost of Digits: Number Normalization and WER in ASR Systems](https://mlsanity.com/paper/2609.21084/) (2026)

## Abstract (arXiv)

Self-supervised learning has been proved to benefit a wide range of speech processing tasks, such as speech recognition/translation, speaker verification and diarization, etc. However, most of current approaches are computationally expensive. In this paper, we propose a simplified and more efficient self-supervised learning framework termed as NeMo Encoder for Speech Tasks (NEST). Specifically, we adopt the FastConformer architecture with 8x sub-sampling rate, which is faster than Transformer or Conformer architectures. Instead of clustering-based quantization, we use fixed random projection for its simplicity and effectiveness. We also implement a generalized noisy speech augmentation that teaches the model to disentangle the main speaker from noise or other speakers. Experiments show that model improves over existing self-supervised models and achieves new state-of-the-art performance on a variety of speech processing tasks, such as speech recognition/translation, speaker diarization, spoken language understanding, etc. Code and checkpoints are publicly available via NVIDIA NeMo framework.