专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

WO2006114101A1 DETECTION OF SPEECH PRESENT IN A NOISY SIGNAL AND SPEECH ENHANCEMENT MAKING USE THEREOF 审中-公开
标题翻译：语音信号检测和声音增强功能的检测
公开(公告)号：WO2006114101A1
公开(公告)日：2006-11-02
申请号：PCT/DK2006/000221
申请日：2006-04-26
申请人： AALBORG UNIVERSITET , ANDERSEN, Søren, Vang , SØRENSEN, Karsten, Vandborg
发明人： ANDERSEN, Søren, Vang , SØRENSEN, Karsten, Vandborg
IPC分类号： G10L21/02 , G10L11/02
CPC分类号： G10L25/78 , G10L21/0208
摘要： The invention provides a method for speech presence detection of speech in a noisy signal. Based on the noisy signal represented as a temporal-spectral distribution, the method includes performing a temporal-spectral smoothing on the temporal-spectral representation of the noisy signal prior to making a speech presence decision. This allows detection of connected regions in the time-frequency domain representation of the noisy signal, and thus allows improved possibilities for efficient noise suppression without musical tones as resulting artifacts. In preferred embodiments, the temporal-spectral smoothing includes performing a spectral smoothing prior to performing a temporal smoothing, and preferably the temporal smoothing includes performing a recursive smoothing with time and frequency varying smoothing parameters, these parameters being lower limited so as to ensure a minimum degree of smoothing. In preferred embodiments, the speech presence decision is based on a minimum tracking of an output of the temporal-spectral smoothing, and a noise estimation is performed based on the speech presence decision, this decision being a binary decision. The mentioned speech presence decision is advantageous for speech enhancement, especially speech enhancement including applying different attenuation functions to regions detected as noise and speech, respectively. In a preferred embodiment noise regions are attenuated by multiplying by a scalar, e.g. a scalar of 0.05-0.4. The methods are applicable within a number of devices e.g. hearing aids, headset and mobile phones.
摘要翻译：本发明提供了一种用于语音在噪声信号中的语音存在检测的方法。基于表示为时间谱分布的噪声信号，该方法包括在进行语音存在决定之前对噪声信号的时间谱表示执行时间谱平滑。这允许在噪声信号的时间 - 频率域表示中检测连接的区域，并因此允许改进的有效噪声抑制的可能性，而没有音调作为产生的伪像。在优选实施例中，时间 - 频谱平滑包括在执行时间平滑之前执行频谱平滑，并且优选地，时间平滑包括利用随时间和频率变化的平滑参数执行递归平滑，这些参数被限制得较低，以便确保最小平滑度。在优选实施例中，语音存在决定基于时间频谱平滑的输出的最小跟踪，并且基于语音存在决定执行噪声估计，该判定是二进制判定。所提到的语音存在决定对于语音增强特别是语音增强是有利的，包括分别对被检测为噪声和语音的区域应用不同的衰减函数。在优选实施例中，噪声区域通过乘以标量来衰减。标量为0.05-0.4。这些方法适用于多个装置，例如，助听器，耳机和手机。

2. 发明申请

WO2009092709A1 ACOUSTIC ECHO REDUCTION 审中-公开
标题翻译：消声减速
公开(公告)号：WO2009092709A1
公开(公告)日：2009-07-30
申请号：PCT/EP2009/050596
申请日：2009-01-20
申请人： SKYPE LIMITED , SØRENSEN, Karsten Vandborg , BERGENHEIM, Jon , VOS, Koen
发明人： SØRENSEN, Karsten Vandborg , BERGENHEIM, Jon , VOS, Koen
IPC分类号： H04M9/08
CPC分类号： H04M9/085
摘要： A method for removing an echo component in a first signal received at an audio input device, said method comprising the steps of outputting a second signal from an audio output device, receiving at the audio input device the first signal wherein the echo component in the first signal is the result of the second signal traversing an echo path having a frequency response which defines the relationship between the echo component and the second signal; determining an echo path model indicating an estimate of the frequency response of the echo path; removing an estimate of the echo component from the first signal using the echo path model; detecting if the first signal is overloaded; and wherein if it is detected that the first signal is overloaded the step of determining an echo path mode! comprises determining an overload echo path model such that the estimate of the frequency response indicated by the overload echo path mode is only allowed to increase over time regardless of whether the frequency response of the echo path is decreasing over time.
摘要翻译：一种用于去除在音频输入装置接收的第一信号中的回波分量的方法，所述方法包括以下步骤：从音频输出装置输出第二信号，在音频输入装置处接收第一信号，其中第一信号中的回波分量信号是第二信号穿过具有定义回波分量和第二信号之间的关系的频率响应的回波路径的结果; 确定指示回波路径的频率响应的估计的回波路径模型; 使用所述回波路径模型从所述第一信号中去除所述回波分量的估计; 检测第一信号是否过载; 并且其中如果检测到所述第一信号过载，则确定回波路径模式的步骤！包括确定过载回波路径模型，使得由过载回波路径模式指示的频率响应的估计仅被允许随时间增加，而不管回波路径的频率响应是否随时间而减少。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式