发明申请
US20080228477A1 Method and Device For Processing a Voice Signal For Robust Speech Recognition
审中-公开

基本信息:
- 专利标题: Method and Device For Processing a Voice Signal For Robust Speech Recognition
- 专利标题(中):用于处理用于鲁棒语音识别的语音信号的方法和装置
- 申请号:US10585747 申请日:2004-10-04
- 公开(公告)号:US20080228477A1 公开(公告)日:2008-09-18
- 发明人: Tim Fingscheidt , Panji Setiawan , Sorel Stan
- 申请人: Tim Fingscheidt , Panji Setiawan , Sorel Stan
- 专利权人: Siemens Aktiengesellschaft
- 当前专利权人: Siemens Aktiengesellschaft
- 优先权: DE102004001863.4 20040113
- 国际申请: PCT/EP04/52427 WO 20041004
- 主分类号: G10L15/20
- IPC分类号: G10L15/20
摘要:
A speech signal is processed for subsequent speech recognition. The speech signal is tainted by noise and represents at least one speech command. The following steps are executed: a) recording of the noise-tainted speech signal; b) use of noise reduction on the speech signal to generate a noise-reduced speech signal; c) normalization of the noise-reduced speech signal to a target signal value with the aid of a normalization factor, to generate a noise-reduced, normalized speech signal).
摘要(中):
语音信号被处理用于随后的语音识别。 语音信号被噪声污染并且表示至少一个语音命令。 执行以下步骤:a)记录噪声污染的语音信号; b)对语音信号使用降噪以产生噪声降低的语音信号; c)借助于归一化因子将噪声降低的语音信号归一化为目标信号值,以产生噪声降低的归一化语音信号)。
IPC结构图谱:
G | 物理 |
--G10 | 乐器;声学 |
----G10L | 语言分析或合成;语言识别 |
------G10L15/00 | 语音识别 |
--------G10L15/20 | .特别适用于不利环境(例如,噪音环境)中增强语音强度的语音识别技术 |