一种基于分而治之的语音识别错误纠正方案*

介绍了一种基于分而治之的语音识别错误纠正方案，首先利用混淆网络把连续语音识别问题转换为顺序的、独立的分类子任务。每个分类子任务可看做是孤立词识别问题，通过训练专门的支持向量机来区分混淆网络的识别候选。提出了一种快速的基于码本转换的语音向量对齐方法，解决了变长语音向量无法直接作为支持向量机输入的问题。通过一个普通话音节识别任务的实验结果表明，该方案能有效提高系统的正确率。

Speech recognition error correction scheme based on divide-and-conquer

This paper introduced a divide-and-conquer speech recognition error correction scheme. Firstly transformed conti-nuous speech recognition problem into sequential, independent, classification tasks using confusion network(CN). Each of these sub-tasks could be taken as an isolated word recognition problem and specialized support vector machines (SVMs) were trained and applied to each problem to discriminate the recognized candidates from CN. Proposed a fast codebook transformation based speech vector alignment method to address the problem that variable length speech vector could not be directly acted as the input vector for SVM. Experiment on a mandarin syllable recognition task shows the proposed scheme can improve the recognition accuracy effectively.