会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 8. 发明申请
    • MODELING LOUDSPEAKERS BASED ON CASCADING LUMPED PARAMETER MODELS WITH NEURAL NETWORKS
    • 基于具有神经网络的渐变参数模型建模扬声器
    • US20160323685A1
    • 2016-11-03
    • US14702382
    • 2015-05-01
    • HARMAN INTERNATIONAL INDUSTRIES, INC
    • Ajay IYER
    • H04R29/00
    • H04R29/001H03G11/00H04R3/007
    • In one embodiment of the present invention, a loudspeaker modeling subsystem configures a neural lumped parameter loudspeaker (NeLP) model to represent the behavior of a loudspeaker. The NeLP model is implemented as a cascaded combination of a lumped parameter model (LPM) and a neural network (NN) model. To configure the model, the loudspeaker modeling subsystem first estimates values for the parameters used in the LPM. The loudspeaker modeling subsystem then “fixes” these parameters and trains the NN model to act on a predicted output pressure that is generated via the LPM. More specifically, the loudspeaker modeling subsystem configures the NN to modify the predicted output pressure to minimize the error between the predicted output pressure and a measured loudspeaker output pressure. Notably, by strategically fusing the LPM and the NN model, the NeLP model leverages the strengths and mitigates the weaknesses typically associated with conventional loudspeaker modeling techniques.
    • 在本发明的一个实施例中,扬声器建模子系统配置神经集总参数扬声器(NeLP)模型以表示扬声器的行为。 NeLP模型实现为集中参数模型(LPM)和神经网络(NN)模型的级联组合。 要配置模型,扬声器建模子系统首先估计LPM中使用的参数值。 扬声器建模子系统然后“修复”这些参数,并训练NN模型以作用于通过LPM生成的预测输出压力。 更具体地,扬声器建模子系统配置NN以修改预测的输出压力,以使预测输出压力和测量的扬声器输出压力之间的误差最小化。 值得注意的是,通过战略性地融合LPM和NN模型,NeLP模型利用了优势,减轻了与传统扬声器建模技术相关的弱点。
    • 9. 发明授权
    • Dynamic range control gain encoding
    • 动态范围控制增益编码
    • US09276544B2
    • 2016-03-01
    • US14280423
    • 2014-05-16
    • Apple Inc.
    • Frank M. Baumgarte
    • H03G3/00H03G3/20H03G11/00H03G3/32H03G7/00
    • H03G3/20H03G3/001H03G3/32H03G7/007H03G11/00
    • A system and method is provided for converting Dynamic Range Control/Compression (DRC) gain values into a spline representation that is compatible with the current standards. The system and method may: 1) minimize the bitrate for encoding and/or 2) minimize the approximation error between reference gain and interpolation values. A strategy for bitrate minimization may be the reduction of the number of spline nodes since gain and slope information must be transmitted for each node. Accordingly, an efficient heuristics based approach is provided that reduces the number of spline nodes needed to represent a series of DRC gain values using interpolation while accounting for overshoots and other inaccuracies.
    • 提供了一种用于将动态范围控制/压缩(DRC)增益值转换为与当前标准兼容的样条表示的系统和方法。 该系统和方法可以:1)最小化用于编码的比特率和/或2)最小化参考增益和内插值之间的近似误差。 用于比特率最小化的策略可以是减少花键节点的数量,因为必须为每个节点传输增益和斜率信息。 因此,提供了一种基于有效启发法的方法,其减少了使用插值来表示一系列DRC增益值所需的样条节点的数量,同时考虑了过冲和其他不准确性。