# Efficient and Robust Long-Form Speech Recognition with Hybrid H3-Conformer

arXiv: https://arxiv.org/abs/2410.04159 · HTML: https://mlsanity.com/paper/2410.04159/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Oct 2024.

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

- [Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR](https://mlsanity.com/paper/2506.19761/) (2025)
- [TTF: Temporal Token Fusion for Efficient Video-Language Model](https://mlsanity.com/paper/2605.07355/) (2026)

## Abstract (arXiv)

Recently, Conformer has achieved state-of-the-art performance in many speech recognition tasks. However, the Transformer-based models show significant deterioration for long-form speech, such as lectures, because the self-attention mechanism becomes unreliable with the computation of the square order of the input length. To solve the problem, we incorporate a kind of state-space model, Hungry Hungry Hippos (H3), to replace or complement the multi-head self-attention (MHSA). H3 allows for efficient modeling of long-form sequences with a linear-order computation. In experiments using two datasets of CSJ and LibriSpeech, our proposed H3-Conformer model performs efficient and robust recognition of long-form speech. Moreover, we propose a hybrid of H3 and MHSA and show that using H3 in higher layers and MHSA in lower layers provides significant improvement in online recognition. We also investigate a parallel use of H3 and MHSA in all layers, resulting in the best performance.