公开(公告)号：US6012052A

公开(公告)日：2000-01-04

申请号：US7900

申请日：1998-01-15

申请人： Steven J. Altschuler ,  Greg Ridgeway

发明人： Steven J. Altschuler ,  Greg Ridgeway

IPC分类号： G06F17/30 ,  G06F17/00

CPC分类号： G06F17/30902 ,  Y10S707/99932 ,  Y10S707/99943 ,  Y10S707/99953

摘要： Building resource (e.g., Internet content) and attribute transition probability models and using such models for pre-fetching resources, editing resource link topology, building resource link topology templates, and collaborative filtering.

摘要翻译： 构建资源（例如互联网内容）和属性转换概率模型，并使用这些模型来预取资源，编辑资源链路拓扑，构建资源链路拓扑模板和协同过滤。

公开(公告)号：US06216154B1

公开(公告)日：2001-04-10

申请号：US09065963

申请日：1998-04-24

申请人： Steven J. Altschuler ,  David Ingerman

发明人： Steven J. Altschuler ,  David Ingerman

IPC分类号： G06F1730

CPC分类号： G06F11/3452 ,  G06F2201/875 ,  Y10S707/99935

摘要： Entering and evaluating group(s) of similar dependence hypotheses, such as time dependence hypotheses, and forecasting values of a variable based on the group(s) of similar dependence hypotheses. The group(s) of similar dependence hypotheses may be used to forecast requests for an Internet resource or Internet resources having one or more particular attributes. The entered group(s) of similar dependence hypotheses may be evaluated based on known data, such as past requests for Internet resources or Internet resources of a particular type.

摘要翻译： 根据类似依赖假设的组，输入和评估类似依赖假设的组，如时间相关假设和变量的预测值。 类似依赖假设的组可以用于预测具有一个或多个特定属性的因特网资源或互联网资源的请求。 可以基于已知数据来评估输入的相似依赖假设的组，例如对于特定类型的因特网资源或因特网资源的过去请求。

公开(公告)号：US07047189B2

公开(公告)日：2006-05-16

申请号：US10992051

申请日：2004-11-18

申请人： Alejandro Acero ,  Steven J. Altschuler ,  Lani Fang Wu

发明人： Alejandro Acero ,  Steven J. Altschuler ,  Lani Fang Wu

IPC分类号： G10L19/12

CPC分类号： G10L25/78 ,  G10L21/0264 ,  G10L2021/02082 ,  G10L2021/02161

摘要： Sound source separation, without permutation, using convolutional mixing independent component analysis based on a priori knowledge of the target sound source is disclosed. The target sound source can be a human speaker. The reconstruction filters used in the sound source separation take into account the a priori knowledge of the target sound source, such as an estimate the spectra of the target sound source. The filters may be generally constructed based on a speech recognition system. Matching the words of the dictionary of the speech recognition system to a reconstructed signal indicates whether proper separation has occurred. More specifically, the filters may be constructed based on a vector quantization codebook of vectors representing typical sound source patterns. Matching the vectors of the codebook to a reconstructed signal indicates whether proper separation has occurred. The vectors may be linear prediction vectors, among others.

摘要翻译： 公开了基于目标声源的先验知识的声源分离，不排列，使用卷积混合独立分量分析。 目标声源可以是人的扬声器。 在声源分离中使用的重建滤波器考虑了目标声源的先验知识，例如估计目标声源的频谱。 滤波器通常可以基于语音识别系统来构造。 将语音识别系统的词典与重构的信号进行匹配，表示是否发生了适当的分离。 更具体地说，滤波器可以基于表示典型声源模式的矢量的矢量量化码本构成。 将码本的向量与重构信号进行匹配，表示是否发生了适当的分离。 矢量可以是线性预测矢量等等。

公开(公告)号：US06879952B2

公开(公告)日：2005-04-12

申请号：US09842416

申请日：2001-04-25

申请人： Alejandro Acero ,  Steven J. Altschuler ,  Lani Fang Wu

发明人： Alejandro Acero ,  Steven J. Altschuler ,  Lani Fang Wu

IPC分类号： G10L11/02 ,  G10L21/02 ,  G10L19/12

CPC分类号： G10L25/78 ,  G10L21/0264 ,  G10L2021/02082 ,  G10L2021/02161

摘要： Sound source separation, without permutation, using convolutional mixing independent component analysis based on a priori knowledge of the target sound source is disclosed. The target sound source can be a human speaker. The reconstruction filters used in the sound source separation take into account the a priori knowledge of the target sound source, such as an estimate the spectra of the target sound source. The filters may be generally constructed based on a speech recognition system. Matching the words of the dictionary of the speech recognition system to a reconstructed signal indicates whether proper separation has occurred. More specifically, the filters may be constructed based on a vector quantization codebook of vectors representing typical sound source patterns. Matching the vectors of the codebook to a reconstructed signal indicates whether proper separation has occurred. The vectors may be linear prediction vectors, among others.

摘要翻译： 公开了基于目标声源的先验知识的声源分离，不排列，使用卷积混合独立分量分析。 目标声源可以是人的扬声器。 在声源分离中使用的重建滤波器考虑了目标声源的先验知识，例如估计目标声源的频谱。 滤波器通常可以基于语音识别系统来构造。 将语音识别系统的词典与重构的信号进行匹配，表示是否发生了适当的分离。 更具体地说，滤波器可以基于表示典型声源模式的矢量的矢量量化码本构成。 将码本的向量与重构信号进行匹配，表示是否发生了适当的分离。 矢量可以是线性预测矢量等等。