# Improving Streaming Speech Recognition With Time-Shifted Contextual Attention And Dynamic Right Context Masking

arXiv: https://arxiv.org/abs/2502.15158 · HTML: https://mlsanity.com/paper/2502.15158/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Feb 2025.

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

- [Dynamic Context-Aware Streaming Pretrained Language Model For Inverse Text Normalization](https://mlsanity.com/paper/2505.24229/) (2025)
- [Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization](https://mlsanity.com/paper/2604.19079/) (2026)
- [Towards Efficient Simultaneous Inverse Text Normalization with Pretrained Text-to-Text Language Model and Read-Tag-Write Policy](https://mlsanity.com/paper/2610.19492/) (2026)

## Abstract (arXiv)

Chunk-based inference stands out as a popular approach in developing real-time streaming speech recognition, valued for its simplicity and efficiency. However, because it restricts the model's focus to only the history and current chunk context, it may result in performance degradation in scenarios that demand consideration of future context. Addressing this, we propose a novel approach featuring Time-Shifted Contextual Attention (TSCA) and Dynamic Right Context (DRC) masking. Our method shows a relative word error rate reduction of 10 to 13.9% on the Librispeech dataset with the inclusion of in-context future information provided by TSCA. Moreover, we present a streaming automatic speech recognition pipeline that facilitates the integration of TSCA with minimal user-perceived latency, while also enabling batch processing capability, making it practical for various applications.