# Exploring RWKV for Memory Efficient and Low Latency Streaming ASR

arXiv: https://arxiv.org/abs/2309.14758 · HTML: https://mlsanity.com/paper/2309.14758/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Sep 2023.

## Built on by (most cited first, 5 of 5)

- [A Survey on Multimodal Wearable Sensor-based Human Action Recognition](https://mlsanity.com/paper/2404.15349/) (2024)
- [A Survey of RWKV](https://mlsanity.com/paper/2412.14847/) (2024)
- [Joint Fine-tuning and Conversion of Pretrained Speech and Language Models towards Linear Complexity](https://mlsanity.com/paper/2410.06846/) (2024)
- [RWKVTTS: Yet another TTS based on RWKV-7](https://mlsanity.com/paper/2504.03289/) (2025)
- [Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR](https://mlsanity.com/paper/2506.19761/) (2025)

## Abstract (arXiv)

Recently, self-attention-based transformers and conformers have been introduced as alternatives to RNNs for ASR acoustic modeling. Nevertheless, the full-sequence attention mechanism is non-streamable and computationally expensive, thus requiring modifications, such as chunking and caching, for efficient streaming ASR. In this paper, we propose to apply RWKV, a variant of linear attention transformer, to streaming ASR. RWKV combines the superior performance of transformers and the inference efficiency of RNNs, which is well-suited for streaming ASR scenarios where the budget for latency and memory is restricted. Experiments on varying scales (100h - 10000h) demonstrate that RWKV-Transducer and RWKV-Boundary-Aware-Transducer achieve comparable to or even better accuracy compared with chunk conformer transducer, with minimal latency and inference memory cost.