arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2201.10190eess.AScs.SD
收藏

一种新的流编解码器块同步解码算法--游程-返回缝合搜索(Run-and-Back Stitch Search)ASR

Run-and-back stitch search: novel block synchronous decoding for streaming encoder-decoder ASR

Emiru Tsunoo, Chaitanya Narisetty, Michael Hentschel, Yosuke Kashiwagi, Shinji Watanabe

摘要:

编码器-解码器自动语音识别(ASR)系统的流式推理对于减少延迟是重要的,这对于交互式用例是必要的。为此,我们提出了一种新的块同步解码算法,结合端点预测和端点后确定的混合方法。在端点预测中,我们使用CTC后验来计算当前块的编码器特征中尚未发出的令牌数量的期望值。基于期望值,解码器预测端点以实现连续块同步,作为运行缝合。同时,端点后确定概率检测源-目标注意的后跳,这是由端点的错误预测。然后,它通过丢弃这些假设来恢复解码,如回缝。我们将这些方法结合成一个混合的方法,即运行和返回缝合搜索,这降低了计算成本和延迟。各种ASR任务的评估显示了我们提出的解码算法的效率,该算法实现了延迟减少,例如在Librispeech测试集中从1487 ms到821 ms的第90百分位数,同时保持了较高的识别精度。

英文摘要:

A streaming style inference of encoder-decoder automatic speech recognition (ASR) system is important for reducing latency, which is essential for interactive use cases. To this end, we propose a novel blockwise synchronous decoding algorithm with a hybrid approach that combines endpoint prediction and endpoint post-determination. In the endpoint prediction, we compute the expectation of the number of tokens that are yet to be emitted in the encoder features of the current blocks using the CTC posterior. Based on the expectation value, the decoder predicts the endpoint to realize continuous block synchronization, as a running stitch. Meanwhile, endpoint post-determination probabilistically detects backward jump of the source-target attention, which is caused by the misprediction of endpoints. Then it resumes decoding by discarding those hypotheses, as back stitch. We combine these methods into a hybrid approach, namely run-and-back stitch search, which reduces the computational cost and latency. Evaluations of various ASR tasks show the efficiency of our proposed decoding algorithm, which achieves a latency reduction, for instance in the Librispeech test set from 1487 ms to 821 ms at the 90th percentile, while maintaining a high recognition accuracy.

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。

↑