发明名称 |
Method for segmenting audio signals |
摘要 |
An input signal is converted to a feature-space representation. The feature-space representation is projected onto a discriminant subspace using a linear discriminant analysis transform to enhance the separation of feature clusters. Dynamic programming is used to find global changes to derive optimal cluster boundaries. The cluster boundaries are used to identify the segments of the audio signal.
|
申请公布号 |
US8521529(B2) |
申请公布日期 |
2013.08.27 |
申请号 |
US20050907851 |
申请日期 |
2005.04.18 |
申请人 |
GOODWIN MICHAEL M.;LAROCHE JEAN;CREATIVE TECHNOLOGY LTD |
发明人 |
GOODWIN MICHAEL M.;LAROCHE JEAN |
分类号 |
G10L15/06 |
主分类号 |
G10L15/06 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
|