Application of Subword Duration Features in Telephone Speech Verification 子词驻留特征在电话语音确认中的应用
This paper shows that the traditional parallelization techniques can be used to exploit subword parallelism, and also proposes a novel method to extract subword parallelism based on the cost subgraph. 本文说明传统的并行技术可以有效地开发循环中的子字并行性,同时提出一种基于代价子图的子字并行指令自动识别的方法。
Experimental results show that Uyghur speech recognition based on subword can gain better recognition results. 实验结果表明,基于子字单元的维吾尔语语音识别可以获得更好的识别结果。
A language is dense if every word is a subword of some word in the language. 一个语言称为稠密的如果每个字都是该语言中某个字的一个小字。
The robustness and accuracy of generating subword units are proved by experiments. The results show that the algorithm has a better performance on the two aspects, and is independent of speakers. 通过实验验证了子词单元产生的稳定性和准确性,实验结果表明,算法在这两方面均达到了较好的性能,且与话者无关。