公开(公告)号：US20060111899A1

公开(公告)日：2006-05-25

申请号：US10995835

申请日：2004-11-23

申请人： Kabi Padhi ,  Sudhir Kumar ,  Sapna George

发明人： Kabi Padhi ,  Sudhir Kumar ,  Sapna George

IPC分类号： G10L19/12

CPC分类号： G10L19/005

摘要： A method includes receiving a sequence of frames containing audio information and determining that a frame is missing in the sequence of frames. The method also includes comparing the frame that precedes the missing frame to the received frames to identify a selected frame. The method further includes identifying a replacement frame comprising the frame that follows the selected frame. In addition, the method includes inserting the replacement frame into the sequence of frames in place of the missing frame.

摘要翻译： 一种方法包括：接收包含音频信息的帧序列，并确定帧序列中帧丢失。 该方法还包括将丢失帧之前的帧与接收的帧进行比较以识别所选择的帧。 该方法还包括识别包括跟随所选帧的帧的替换帧。 此外，该方法包括将替换帧插入到帧序列中而不是丢失的帧。

公开(公告)号：US20050273328A1

公开(公告)日：2005-12-08

申请号：US10955959

申请日：2004-09-30

申请人： Kabi Padhi ,  Sapna George

发明人： Kabi Padhi ,  Sapna George

IPC分类号： G10L15/08 ,  G10L15/10

CPC分类号： G10H1/40 ,  G10H2210/076 ,  G10H2240/135 ,  G10L15/10

摘要： An energy-based pattern recognition algorithm receives the input frames of an audio signal and a test frame sequence and returns a best match in the audio signal to the given test frame sequence. The energy of each input frame is computed and input frames for which the energy is both within a predetermined degree of closeness to the local maximum energy within the test frame sequence and a local maximum within a respective neighborhood of adjacent frames are identified as probable matches. The difference between overall energy for frames neighboring the remaining probable matches and the test frame sequence is computed as a percentage. The best match is selected based on a weighted combination of difference between local maximum energies and minimum percent deviation in overall energy. Local signal characteristic matching may be employed, with weighting, to refine matching.

摘要翻译： 基于能量的模式识别算法接收音频信号和测试帧序列的输入帧，并将音频信号中的最佳匹配返回给给定的测试帧序列。 计算每个输入帧的能量，并且将能量都在与测试帧序列内的局部最大能量接近的预定程度内的相邻帧的相邻邻域内的局部最大值的输入帧识别为可能的匹配。 与剩余可能匹配相邻的帧的总体能量与测试帧序列之间的差异以百分比计算。 基于局部最大能量和总能量的最小百分比偏差的加权组合来选择最佳匹配。 可以采用本地信号特征匹配，具有加权，以精细匹配。

公开(公告)号：US20050096899A1

公开(公告)日：2005-05-05

申请号：US10700872

申请日：2003-11-04

申请人： Kabi Padhi ,  Sapna George

发明人： Kabi Padhi ,  Sapna George

IPC分类号： G10L15/10 ,  H04R29/00

CPC分类号： G10L15/10 ,  G10L25/06

摘要： An apparatus, method, and computer program are capable of receiving and cross-correlating a first audio signal and a second audio signal. This produces a cross-correlated signal, which is used to identify a plurality of parameters associated with at least one of the first and second audio signals. The parameters are used to generate an indicator identifying an extent to which the first and second audio signals match.

摘要翻译： 装置，方法和计算机程序能够接收和互相关联第一音频信号和第二音频信号。 这产生交叉相关信号，其用于识别与第一和第二音频信号中的至少一个相关联的多个参数。 这些参数用于产生识别第一和第二音频信号匹配的程度的指示符。

公开(公告)号：US20050273326A1

公开(公告)日：2005-12-08

申请号：US10955904

申请日：2004-09-30

申请人： Kabi Padhi ,  Sapna George

发明人： Kabi Padhi ,  Sapna George

IPC分类号： G10L15/02 ,  G10L15/08

CPC分类号： G10L15/02

摘要： An energy-based pattern recognition algorithm receives the input frames of an audio signal and a test frame sequence and returns a best match in the audio signal to the given test frame sequence. The energy of each input frame is computed, and input frames for which the energy is within a predetermined degree of closeness to the local maximum energy within the test frame sequence are identified as probable matches. Probable matches are then eliminated if the respective probable match does not correspond to a local maximum within a respective neighborhood of adjacent frames. The difference between overall energy for frames neighboring the remaining probable matches and the test frame sequence is computed as a percentage, with the minimum percent deviation in energy from the test frame sequence being returned as the best pattern match. Local signal characteristic matching may be employed to refine matching.

摘要翻译： 基于能量的模式识别算法接收音频信号和测试帧序列的输入帧，并将音频信号中的最佳匹配返回给给定的测试帧序列。 计算每个输入帧的能量，并且将能量在与测试帧序列内的局部最大能量接近的预定程度内的输入帧识别为可能的匹配。 如果相应的可能匹配不对应于相邻帧的相应邻域内的局部最大值，则可以消除可能的匹配。 计算与剩余可能匹配相邻的帧的总体能量与测试帧序列之间的差异作为百分比计算，随着最佳模式匹配，返回测试帧序列的能量的最小百分比偏差。 可以采用本地信号特征匹配来优化匹配。

公开(公告)号：US20060112811A1

公开(公告)日：2006-06-01

申请号：US10999376

申请日：2004-11-30

申请人： Kabi Padhi ,  Jianhua Sun

发明人： Kabi Padhi ,  Jianhua Sun

IPC分类号： G10H7/00

CPC分类号： G10H7/08 ,  G10H2210/066 ,  G10H2230/021 ,  G10H2250/615

摘要： A method includes receiving an audio signal and identifying one or more steady-state segments of the audio signal. The method also includes identifying at least one portion of the one or more segments that contains a specified frequency. Further, the method includes generating a wavetable using the at least one identified portion of the one or more segments. In addition, the method could include synthesizing an output audio signal using the wavetable. The output audio signal could represent a ringtone in a mobile telephone.