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

US07009935B2 Transmission over packet switched networks 有权
标题翻译：通过分组交换网络进行传输
公开(公告)号：US07009935B2
公开(公告)日：2006-03-07
申请号：US09852939
申请日：2001-05-09
申请人： Tina Abrahamsson , Soren Vang Andersen , Roar Hagen , W. Bastiaan Kleijn
发明人： Tina Abrahamsson , Soren Vang Andersen , Roar Hagen , W. Bastiaan Kleijn
IPC分类号： H04L12/28 , H04L12/66 , G10L21/00
CPC分类号： H04L12/6418 , H04L2012/6481
摘要： The invention relates to methods for encoding/decoding a digitized sound signal which is transmitted over a packet switched network in such a way that diversity is provided. Each sound segment of the digitized sound signal is encoded into at least two different segment descriptions, i.e. into different representations of the sound signal segment. The segment descriptions differ from each other in that they provide different quantization values for a digital sound signal sample. The different segment descriptions are transmitted in separate data packets over the network at different points of time.
摘要翻译：本发明涉及通过分组交换网络以提供分集的方式对数字化声音信号进行编码/解码的方法。数字化声音信号的每个声音段被编码成至少两个不同的段描述，即声音信号段的不同表示。段描述彼此不同之处在于它们为数字声音信号样本提供不同的量化值。不同的段描述在不同的时间点通过网络在单独的数据分组中传输。

2. 发明授权

US06993481B2 Detection of speech activity using feature model adaptation 有权
标题翻译：使用特征模型适应检测语音活动
公开(公告)号：US06993481B2
公开(公告)日：2006-01-31
申请号：US10006984
申请日：2001-12-04
申请人： Jan K. Skoglund , Jan T. Linden
发明人： Jan K. Skoglund , Jan T. Linden
IPC分类号： G10L15/20 , G10L15/08 , G10L15/06 , G10L15/04
CPC分类号： G10L25/78
摘要： According to the invention, a method for detecting speech activity for a signal is disclosed. In one step, a plurality of features is extracted from the signal. An active speech probability density function (PDF) of the plurality of features is modeled, and an inactive speech PDF of the plurality of features is modeled. The active and inactive speech PDFs are adapted to respond to changes in the signal over time. The signal is probability-based classifyied based, at least in part, on the plurality of features. Speech in the signal is distinguished based, at least in part, upon the probability-based classification.
摘要翻译：根据本发明，公开了一种用于检测信号的语音活动的方法。在一个步骤中，从信号中提取多个特征。对多个特征的活动语音概率密度函数（PDF）进行建模，并且对多个特征的无效语音PDF进行建模。主动和不活动的语音PDF适于响应随时间变化的信号。信号基于概率分类，至少部分地基于多个特征。至少部分地基于概率分类来区分信号中的语音。

3. 发明申请

US20030097256A1 Enhanced coded speech 有权
标题翻译：增强编码语音
公开(公告)号：US20030097256A1
公开(公告)日：2003-05-22
申请号：US10036747
申请日：2001-11-08
申请人： Global IP Sound AB
发明人： W. Bastiaan Kleijn
IPC分类号： G10L011/04
CPC分类号： G10L21/0364
摘要： According to the invention, a method for increasing quality of an enhanced output signal to approximate an undistorted sound signal is disclosed. In one step, a distorted input signal is received that includes an embedded corrupting signal. The embedded corrupting signal is statistically related to the undistorted sound signal. An enhancement signal is determined by finding a difference between the distorted input signal and the enhanced output signal. The enhancement signal attempts to offset the affect of the embedded corrupting signal. Based at least in part upon analyzing the enhancement signal, the enhanced output signal is produced.
摘要翻译：根据本发明，公开了一种用于提高增强输出信号的质量以近似无失真声音信号的方法。在一个步骤中，接收到包含嵌入的破坏信号的失真的输入信号。嵌入式破坏信号与未失真声音信号统计相关。通过找到失真的输入信号和增强的输出信号之间的差来确定增强信号。增强信号试图抵消嵌入式破坏信号的影响。至少部分地基于分析增强信号，产生增强的输出信号。

4. 发明授权

US06970479B2 Encoding and decoding of a digital signal 有权
标题翻译：数字信号的编码和解码
公开(公告)号：US06970479B2
公开(公告)日：2005-11-29
申请号：US09853883
申请日：2001-05-10
申请人： Tina Abrahamsson , Soren Vang Andersen , Roar Hagen , W. Bastiaan Kleijn
发明人： Tina Abrahamsson , Soren Vang Andersen , Roar Hagen , W. Bastiaan Kleijn
IPC分类号： G10L19/02 , H04J3/24 , G10L19/04 , G10L19/08 , H04J3/07
CPC分类号： G10L19/02
摘要： The invention relates to methods for encoding/decoding of a digital signal which is transmitted over a packet switched network. Prediction samples are generated at the transmitting and receiving end. The digital signal is lossless encoded at the transmitting end, and lossless decoded at the receiving end, based on the quantizations of generated prediction samples. During encoding, the generated prediction samples are quantized separately from the quantization of the digital samples. The predictions are used in the index domain in the form of quantized indices during encoding/decoding of the digital signal.
摘要翻译：本发明涉及通过分组交换网络发送的数字信号的编码/解码方法。在发送和接收端生成预测样本。数字信号在发送端进行无损编码，并根据生成的预测样本的量化在接收端进行无损解码。在编码期间，所生成的预测样本与数字样本的量化分开量化。预测在数字信号的编码/解码期间以量化索引的形式在索引域中使用。

5. 发明申请

US20020165713A1 Detection of sound activity 有权
标题翻译：检测声音活动
公开(公告)号：US20020165713A1
公开(公告)日：2002-11-07
申请号：US10006984
申请日：2001-12-04
申请人： Global IP Sound AB
发明人： Jan K. Skoglund , Jan T. Linden
IPC分类号： G10L015/12
CPC分类号： G10L25/78
摘要： According to the invention, a method for detecting speech activity for a signal is disclosed. In one step, a plurality of features is extracted from the signal. An active speech probability density function (PDF) of the plurality of features is modeled, and an inactive speech PDF of the plurality of features is modeled. The active and inactive speech PDFs are adapted to respond to changes in the signal over time. The signal is probability-based classifyied based, at least in part, on the plurality of features. Speech in the signal is distinguished based, at least in part, upon the probability-based classification.
摘要翻译：根据本发明，公开了一种用于检测信号的语音活动的方法。在一个步骤中，从信号中提取多个特征。对多个特征的活动语音概率密度函数（PDF）进行建模，并且对多个特征的无效语音PDF进行建模。主动和不活动的语音PDF适于响应随时间变化的信号。信号基于概率分类，至少部分地基于多个特征。至少部分地基于概率分类来区分信号中的语音。

6. 发明申请

US20030091160A1 Network media playout 有权
标题翻译：网络媒体播出
公开(公告)号：US20030091160A1
公开(公告)日：2003-05-15
申请号：US10262531
申请日：2002-09-30
申请人： Global IP Sound AB
发明人： Niklas Enbom , Fredrik Galschiodt
IPC分类号： H04M001/64
CPC分类号： H04L65/604 , H04L12/6418 , H04L29/06 , H04L29/06027 , H04L65/80 , H04L2012/6472 , H04L2012/6481 , H04L2012/6489
摘要： According to the invention, a method for processing an audio media stream that originates from a packet communication network is disclosed. In one step, packets are received as they arrive from the packet communication network. The packets are part of the audio media stream. A playout buffer in a media playout device is monitored. It is determined that the playout buffer is filled below a threshold. A portion of the audio media stream is retrieved when the playout buffer is filled below the threshold. The portion is stored in the playout buffer of the media playout device.
摘要翻译：根据本发明，公开了一种用于处理源自分组通信网络的音频媒体流的方法。在一个步骤中，当数据包从分组通信网络到达时被接收。数据包是音频媒体流的一部分。监视媒体播出设备中的播放缓冲区。确定播放缓冲器被填充到阈值以下。当播放缓冲器被填充到阈值以下时，检索音频媒体流的一部分。该部分存储在媒体播放设备的播放缓冲区中。

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