通过动态关注未来上下文，提升流式语音识别准确率。
Improving Streaming Speech Recognition With Time-Shifted Contextual Attention And Dynamic Right Context Masking
- 引入时间偏移上下文注意力，让模型感知未来信息。
- 在Librispeech上相对词错误率降低10%至13.9%。
- 低延迟集成方案，适合实际部署的流式识别场景。
基于分块的推理是实现实时流式语音识别的常用方法，因其简单高效而受到青睐。然而，该方法仅限制模型关注历史和当前分块上下文，可能在需要考虑未来信息的场景中导致性能下降。为此，我们提出一种新方法，结合时间偏移上下文注意力（TSCA）与动态右文掩码（DRC）。实验表明，TSCA引入上下文未来信息后，在Librispeech数据集上实现了10%至13.9%的相对词错误率降低。此外，我们构建了一个流式自动语音识别流水线，可实现TSCA的轻量集成，用户感知延迟极低，同时支持批量处理，适用于多种实际应用场景。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。