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

US20080208581A1 Model Adaptation System and Method for Speaker Recognition 审中-公开
标题翻译：扬声器识别模型适应系统及方法
公开(公告)号：US20080208581A1
公开(公告)日：2008-08-28
申请号：US10581227
申请日：2004-12-03
申请人： Jason Pelecanos , Subramanian Sridharan , Robert Vogt
发明人： Jason Pelecanos , Subramanian Sridharan , Robert Vogt
IPC分类号： G10L17/00
CPC分类号： G10L17/04
摘要： A system and method for speaker recognition speaker modelling whereby prior speaker information is incorporated into the modelling process, utilising the maximum a posteriori (MAP) algorithm and extending it to contain prior Gaussian component correlation information. Firstly a background model (10) is estimated. Pooled acoustic reference data (11) relating to a specific demographic of speakers (population of interest) from a given total population is then trained via the Expectation Maximization (EM) algorithm (12) to produce a background model (13). The background model (13) is adapted utilising information from a plurality of reference speakers (21) in accordance with the Maximum A Posteriori (MAP) criterion (22). Utilizing MAP estimation technique, the reference speaker data and prior information obtained from the background model parameters are combined to produce a library of adapted speaker models, namely Gaussian Mixture Models (23).
摘要翻译：一种用于说话者识别扬声器建模的系统和方法，其中先前的说话者信息被并入到建模过程中，利用最大后验（MAP）算法并将其扩展为包含先前的高斯分量相关信息。首先估计一个背景模型（10）。然后通过期望最大化（EM）算法（12）训练与给定总人口的特定人群（兴趣人群）有关的汇集的声学参考数据（11）以产生背景模型（13）。背景模型（13）根据最大后验（最大后验）（MAP）标准（22）利用来自多个参考扬声器（21）的信息。利用MAP估计技术，将从背景模型参数获得的参考说话者数据和先验信息相结合，以产生适应的说话者模型库，即高斯混合模型（23）。

2. 发明授权

US06937723B2 Echo detection and monitoring 有权
标题翻译：回波检测和监测
公开(公告)号：US06937723B2
公开(公告)日：2005-08-30
申请号：US10280801
申请日：2002-10-25
申请人： Simon Daniel Boland , James D. Schreuder , Subramanian Sridharan , Michael William Mason , James Allen Cook
发明人： Simon Daniel Boland , James D. Schreuder , Subramanian Sridharan , Michael William Mason , James Allen Cook
IPC分类号： H04M1/00 , H04B3/23
CPC分类号： H04B3/23
摘要： Echo detection and monitoring systems and methods are provided. According to the invention, the outgoing and incoming voice bearer channels of a voice communication are monitored. The outgoing and incoming signals are time aligned, and measures are then taken to determine whether echo is present in the signal. In accordance with an embodiment of the present invention, the outgoing signal is fed through an adaptive filter.
摘要翻译：提供回波检测和监测系统和方法。根据本发明，监视语音通信的输出和输入语音承载信道。输出和输入信号是时间对齐的，然后采取措施来确定信号中是否存在回波。根据本发明的实施例，输出信号通过自适应滤波器馈送。

3. 发明申请

US20070179784A1 Dynamic match lattice spotting for indexing speech content 审中-公开
标题翻译：用于索引语音内容的动态匹配格点
公开(公告)号：US20070179784A1
公开(公告)日：2007-08-02
申请号：US11377327
申请日：2006-03-16
申请人： Albert Joseph Thambiratnam , Subramanian Sridharan
发明人： Albert Joseph Thambiratnam , Subramanian Sridharan
IPC分类号： G10L15/28
CPC分类号： G10L15/26 , G10L2015/025
摘要： A system for indexing and searching speech content, the system includes two distinct stages, a speech indexing stage (100) and a speech retrieval stage (200). A phone lattice (103) is generated by passing speech content (101) through a speech recogniser (102). The resulting phone lattice is then processed to produce a set of observed sequences Q=(Θ,i) where Θ are the set of observed phone sequences for each node i in the phone lattice. During the retrieval stage (200), a user first inputs a target word (205) into the system, which is then reduced to a target phone sequence P=(p1, p2, . . . , pN) (207). The system then compares target sequence P with the set of observed sequences Q (208), suitably by scoring each observed sequence against the target sequence using a Minimum Edit Distance (MED) calculation to produce a set of matching sequences R (209).
摘要翻译：一种用于索引和搜索语音内容的系统，该系统包括两个不同的阶段，语音索引阶段（100）和语音检索阶段（200）。通过语音识别器（102）传递语音内容（101）来生成电话格（103）。所得到的电话格子然后被处理以产生一组观察到的序列Q =（Theta，i），其中Theta是电话格中每个节点i的观察到的电话序列的集合。在检索阶段（200）期间，用户首先将目标字（205）输入到系统中，然后将目标字（205）减少到目标电话序列P =（p1> 1，p2 < / SUB>，...，p N N N）（207）。然后，系统通过使用最小编辑距离（MED）计算来针对目标序列评估每个观察到的序列以产生一组匹配序列R（209），将目标序列P与观察序列集合Q（208）进行比较。

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