In this paper,we propose a new feature normalization approach for robust speech recognition.
该文提出了一种新的用于鲁棒性语音识别的特征规整方法。
参考来源 - 倒谱形状规整在噪声鲁棒性语音识别中的应用In this paper,two compensation approaches based on feature normalization and score normalization are presented,respectively.
本文提出了从特征规整和评分规整两个方面进行补偿的方法。
参考来源 - 基于特征规整和评分规整的说话人确认研究 in C·2,447,543篇论文数据,部分数据来源于NoteExpress
本文提出了从特征规整和评分规整两个方面进行补偿的方法。
In this paper, two compensation approaches based on feature normalization and score normalization are presented, respectively.
具体包括草图前处理、特征点的检测、笔划分段、图元识别、图元重构、图元规整、端点校正等内容。
The system integrates several process like sketch preprocessing, feature points detection, strokes fragment, primitives recognition, shape reconstruction, and primitives beautification.
系统提取的音频信号特征为线性预测美尔倒谱系数(LPCMCC),采用动态时间规整(DTW)的识别算法。
The audio signal feature, in this scheme, is the LPC Mel Cepstrum Coefficient (LPCMCC) and recognition algorithm is Dynamic Time Warping (DTW).
应用推荐