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 physics/0507044physics.data-anphysics.comp-ph
收藏

非线性降噪对语音识别的改进

Improvement of speech recognition by nonlinear noise reduction

Krzysztof Urbanowicz, Holger Kantz

摘要:

成功的非线性降噪应用到一个单一的通道记录的人类声音的商业语音识别程序的识别率相比,最佳的线性滤波器来衡量。的非线性方法的整体性能被证明是优越的。因此,我们表明,它的根源在非线性确定性动力学理论的算法具有很大的潜力,在实际应用中。

英文摘要:

The success of nonlinear noise reduction applied to a single channel recording of human voice is measured in terms of the recognition rate of a commercial speech recognition program in comparison to the optimal linear filter. The overall performance of the nonlinear method is shown to be superior. We hence demonstrate that an algorithm which has its roots in the theory of nonlinear deterministic dynamics possesses a large potential in a realistic application.

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。

↑