# Early Attentive Sparsification Accelerates Neural Speech Transcription

arXiv: https://arxiv.org/abs/2506.15912 · HTML: https://mlsanity.com/paper/2506.15912/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 24 references that are in the map.
- First posted on arXiv 18 Jun 2025.

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models](https://mlsanity.com/paper/2306.14048/) (2023)
- [Deep Speech 2: End-to-End Speech Recognition in English and Mandarin](https://mlsanity.com/paper/1512.02595/) (2015)
- [SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning](https://mlsanity.com/paper/2012.09852/) (2020)
- [Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages](https://mlsanity.com/paper/2303.01037/) (2023)
- [End-to-End Speech Recognition: A Survey](https://mlsanity.com/paper/2303.03329/) (2023)
- [Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition](https://mlsanity.com/paper/2305.05084/) (2023)
- [Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo Labelling](https://mlsanity.com/paper/2311.00430/) (2023)
- [Pruned RNN-T for fast, memory-efficient ASR training](https://mlsanity.com/paper/2206.13236/) (2022)
- [Anatomy of Industrial Scale Multilingual ASR](https://mlsanity.com/paper/2404.09841/) (2024)
- [LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation](https://mlsanity.com/paper/2502.20583/) (2025)

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

- [MURMUR: An Efficient Inference System for Long-Form ASR](https://mlsanity.com/paper/2606.01483/) (2026)
- [Stride-k Subsampling: Train-Free Audio Token Reduction for Whisper](https://mlsanity.com/paper/2608.30927/) (2026)

## Abstract (arXiv)

Transformer-based neural speech processing has achieved state-of-the-art performance. Since speech audio signals are known to be highly compressible, here we seek to accelerate neural speech transcription by time-domain signal sparsification early in the neural encoding stage, taking advantage of the interpretability of the self-attention mechanism in transformer audio encoders. With the Whisper family of models, we perform a systematic architecture search over the joint space of sparsification stage (a certain encoder layer) and compression ratio (sparsity). We found that the best resulting solutions under 1% accuracy degradation choose to sparsify the hidden state to 40-60% sparsity at an early encoding stage, and thereby achieve up to 1.6x runtime acceleration in English speech transcription tasks on Nvidia GPUs without any fine-tuning.