arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.09063cs.SDeess.AS
收藏

一种基于WFST的自动语音识别异步解码器

An Asynchronous WFST-Based Decoder For Automatic Speech Recognition

Northwestern Polytechnical University(西北工业大学);Johns Hopkins University(约翰斯·霍普金斯大学);Xiaomi Corporation(小米公司);Shanghai Jiao Tong University(上海交通大学)

Hang Lv, Zhehuai Chen, Hainan Xu, Daniel Povey, Lei Xie, Sanjeev Khudanpur

摘要:

本文介绍了一种异步动态解码器,它采用一种高效的A* 算法,在大词汇量连续语音识别的一次解码中加入大语言模型。与可能引起显著计算开销的具有即时合成解码器的标准单遍解码不同,异步动态解码器具有新颖的设计,其中其具有两个前端,一个执行“探索”而另一个执行“回填”。两个前沿的计算在解码过程中交替进行,从而比具有动态合成解码器的标准一遍解码更有效地修剪。实验结果表明,该解码器比标准的on-the-fly复合解码器的单遍解码速度快得多,而且随着数据复杂度的增加,这种加速效果更加明显。

英文摘要:

We introduce asynchronous dynamic decoder, which adopts an efficient A* algorithm to incorporate big language models in the one-pass decoding for large vocabulary continuous speech recognition. Unlike standard one-pass decoding with on-the-fly composition decoder which might induce a significant computation overhead, the asynchronous dynamic decoder has a novel design where it has two fronts, with one performing "exploration" and the other "backfill". The computation of the two fronts alternates in the decoding process, resulting in more effective pruning than the standard one-pass decoding with an on-the-fly composition decoder. Experiments show that the proposed decoder works notably faster than the standard one-pass decoding with on-the-fly composition decoder, while the acceleration will be more obvious with the increment of data complexity.

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。

↑