arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2312.09463cs.CL
收藏

面向多阶段ASR的部分重写方法

Partial Rewriting for Multi-Stage ASR

Google LLC(谷歌有限责任公司)

Antoine Bruguier, David Qiu, Yanzhang He

AI总结:

针对多阶段流式ASR中中间流式结果质量未提升的问题,提出融合两类模型输出的文本处理算法,在无额外延迟、不改最终结果的前提下提升流式结果质量约10%,且无需重训练、适配性广。

摘要:

对于许多流式自动语音识别(ASR)任务而言,在生成高质量最终结果的同时提供及时的中间流式结果至关重要。这一目标可通过多阶段架构实现:小型仅左上下文模型生流式结果,更大的左右上下文模型在末尾生成最终结果。该架构虽能在不牺牲系统流式输出延迟的前提下显著提升最终结果质量,但流式结果并未受益于质量提升。本文提出一种文本处理算法,融合两类模型的流式输出,在不改变最终结果的情况下将流式结果质量提升约10%。该方法无额外延迟、可减少结果闪烁,且轻量无需重新训练模型,可适用于多种多阶段架构。

英文摘要:

For many streaming automatic speech recognition tasks, it is important to provide timely intermediate streaming results, while refining a high quality final result. This can be done using a multi-stage architecture, where a small left-context only model creates streaming results and a larger left- and right-context model produces a final result at the end. While this significantly improves the quality of the final results without compromising the streaming emission latency of the system, streaming results do not benefit from the quality improvements. Here, we propose using a text manipulation algorithm that merges the streaming outputs of both models. We improve the quality of streaming results by around 10%, without altering the final results. Our approach introduces no additional latency and reduces flickering. It is also lightweight, does not require retraining the model, and it can be applied to a wide variety of multi-stage architectures.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑