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. 发明授权

US06990447B2 Method and apparatus for denoising and deverberation using variational inference and strong speech models 有权
公开(公告)号：US06990447B2
公开(公告)日：2006-01-24
申请号：US09999576
申请日：2001-11-15
申请人： Hagai Attias , John Carlton Platt , Li Deng , Alejandro Acero
发明人： Hagai Attias , John Carlton Platt , Li Deng , Alejandro Acero
IPC分类号： G10L15/08 , G10L15/12 , G10L15/06 , G10L21/02
CPC分类号： G10L21/0208 , G10L2021/02082 , H04R2225/43
摘要： A probability distribution for speech model parameters, such as auto-regression parameters, is used to identify a distribution of denoised values from a noisy signal. Under one embodiment, the probability distributions of the speech model parameters and the denoised values are adjusted to improve a variational inference so that the variational inference better approximates the joint probability of the speech model parameters and the denoised values given a noisy signal. In some embodiments, this improvement is performed during an expectation step in an expectation-maximization algorithm. The statistical model can also be used to identify an average spectrum for the clean signal and this average spectrum may be provided to a speech recognizer instead of the estimate of the clean signal.

2. 发明授权

US07076503B2 Managing media objects in a database 失效
公开(公告)号：US07076503B2
公开(公告)日：2006-07-11
申请号：US10021255
申请日：2001-12-19
申请人： John Carlton Platt , Jonathan Kagle , Hagai Attias , Victoria Elizabeth Milton
发明人： John Carlton Platt , Jonathan Kagle , Hagai Attias , Victoria Elizabeth Milton
IPC分类号： G06F17/30
CPC分类号： G06F17/30265 , G06F17/30038 , G06F17/30244 , Y10S707/99944
摘要： A method and apparatus are provided for organizing media objects in a database using contextual information for a media object and known media objects, categories, indexes and searches, to arrive at an inference for cataloging the media object in a database. The media object may then be cataloged in the database according to the inference. A method and apparatus are provided for clustering media objects by forming groups of unlabeled data and applying a distance metric to said group.

3. 发明授权

US06192360B1 Methods and apparatus for classifying text and for building a text classifier 失效
标题翻译：分类文本和构建文本分类器的方法和设备
公开(公告)号：US06192360B1
公开(公告)日：2001-02-20
申请号：US09102946
申请日：1998-06-23
申请人： Susan T. Dumais , David Heckerman , Eric Horvitz , John Carlton Platt , Mehran Sahami
发明人： Susan T. Dumais , David Heckerman , Eric Horvitz , John Carlton Platt , Mehran Sahami
IPC分类号： G06F1700
CPC分类号： G06F17/30707 , G06K9/6269 , Y10S707/99936
摘要： A text classifier and building the text classifier by determining appropriate parameters for the text classifier.
摘要翻译：文本分类器，并通过确定文本分类器的适当参数构建文本分类器。

4. 发明授权

US06327581B1 Methods and apparatus for building a support vector machine classifier 失效
标题翻译：用于构建支持向量机分类器的方法和装置
公开(公告)号：US06327581B1
公开(公告)日：2001-12-04
申请号：US09055477
申请日：1998-04-06
申请人： John Carlton Platt
发明人： John Carlton Platt
IPC分类号： G06F1518
CPC分类号： G06K9/6269 , G06K9/6256 , G06N99/005
摘要： Solving a quadratic programming problem involved in training support vector machines by sweeping through a set of training examples, solving small sub-problems of the quadratic programming problem. Each of these sub-problems has an analytic solution, which is faster that the numerical quadratic programming solutions used in the prior art. In one embodiment, training examples with non-optimal Lagrange multipliers are adjusted, one at a time, until all are optimal (e.g. until all examples fulfill the Kuhn-Tucker conditions). In another embodiment, training examples with non-optimal Lagrange multipliers are paired and then adjusted, until all are optimal.
摘要翻译：通过扫描一组训练示例来解决训练支持向量机的二次规划问题，解决二次规划问题的小问题。这些子问题中的每一个都有一个分析解决方案，这在现有技术中使用的数字二次规划解决方案更快。在一个实施例中，调整具有非最佳拉格朗日乘数的训练示例，一次一个，直到所有都是最优的（例如，直到所有示例满足Kuhn-Tucker条件）。在另一个实施例中，具有非最佳拉格朗日乘数的训练示例被配对然后被调整，直到全部是最优的。

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