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
    • 4. 发明申请
    • IMPROVED METHOD, APPARATUS AND SYSTEM FOR EMBEDDING DATA WITHIN A DATA STREAM
    • 用于在数据流中嵌入数据的改进的方法,设备和系统
    • WO2017103565A1
    • 2017-06-22
    • PCT/GB2016/053796
    • 2016-12-02
    • SONIC DATA LIMITED
    • GOGERLY, Simon
    • G10L19/018
    • G10L19/018
    • The invention resides in a method of placing a code, having a plurality of digits, in original data having media data including audio data, such as a music video, piece of music or music track, to produce coded data. The method determining an area of original data where a digit of the code can be placed to inhibit detection using a placement criteria. A coding strategy determines at least one of the format or location of a digit of the code in coded data. The or each digit of the code has a melodic or sympathetic relationship with a characteristic, such as an audio characteristic, of the corresponding original data in the at the location in which it is placed. Digits are added to the original data and outputting coded data. Similarly, the invention resides in a method for decoding and devices and systems for implementing said methods.
    • 本发明在于一种将具有多个数字的代码放置在具有包括诸如音乐视频,音乐片段或音乐轨道之类的音频数据的媒体数据的原始数据中以产生 编码数据。 该方法确定可以放置代码的数字的原始数据的区域,以使用放置标准来禁止检测。 编码策略确定编码数据中的代码的数字的格式或位置中的至少一个。 该代码的该位或每个数字与放置它的位置处的相应原始数据的特性(例如音频特性)具有旋律或交感关系。 数字被添加到原始数据并输出编码数据。 类似地,本发明在于用于解码的方法以及用于实现所述方法的设备和系统。
    • 7. 发明申请
    • METHOD AND APPARATUS FOR DETERMINING WHETHER A SPECIFIC WATERMARK SYMBOL OUT OF ONE OR MORE CANDIDATE WATERMARK SYMBOLS IS EMBEDDED IN A CURRENT SECTION OF A RECEIVED AUDIO SIGNAL
    • 用于确定一个或多个候选水印符号的特定水印符号被嵌入到接收的音频信号的电流部分中的方法和装置
    • WO2016045977A1
    • 2016-03-31
    • PCT/EP2015/070685
    • 2015-09-10
    • THOMSON LICENSING
    • ARNOLD, MichaelBAUM, Peter GeorgCHEN, XiaomingGRIES, Ulrich
    • G10L19/018
    • G10L19/018
    • From sets of correlation result values it is determined whether a specific watermark symbol out of one or more candidate watermark symbols is embedded in a received audio signal. For all candidate watermark symbols, from each corresponding set of correlation result values, a group (n p ) of maximal values together form a peak vector (v i . From the normalised peak values (w i a probability distribution function (pdf, g(W i )) and a false positive probability function (P fp (w i )) are calculated. If the values of the false positive probability function are smaller than a first threshold value (T min ) / the current candidate watermark symbol is taken as a true watermark symbol. If not yet all candidate watermark symbols have been processed, the next candidate watermark symbol is selected. Otherwise, a minimal value (P* fp ) of the false positive probability functions for all candidate watermark symbols is determined (76) and is compared (77) with a second threshold value (T max ). If it is smaller than the second threshold value, the current candidate watermark symbol is selected. Otherwise, it is determined (78) that no watermark symbol is present.
    • 从相关结果值集合中,确定一个或多个候选水印符号中的特定水印符号是否嵌入在接收到的音频信号中。 对于所有候选水印符号,从每个对应的相关结果值集合,最大值的组(np)一起形成峰值向量(vi。从归一化峰值(wia概率分布函数(pdf,g(W i)) 并计算假阳性概率函数(P fp(wi)),如果假正概率函数的值小于第一阈值(Tmin),则将当前候选水印符号作为真实水印符号,如果 尚未处理所有候选水印符号,选择下一个候选水印符号,否则确定所有候选水印符号的假正概率函数的最小值(P * fp)(76)并进行比较(77) 具有第二阈值(Tmax),如果小于第二阈值,则选择当前候选水印符号,否则确定(78)不存在水印符号。
    • 9. 发明申请
    • REAL-TIME EMOTION RECOGNITION FROM AUDIO SIGNALS
    • 音频信号实时感应识别
    • WO2016014321A1
    • 2016-01-28
    • PCT/US2015/040671
    • 2015-07-16
    • MICROSOFT TECHNOLOGY LICENSING, LLC
    • KHAN, YaserHUYBREGTS, ChrisKIM, JaeyounBUTCHER, Thomas C.
    • G10L25/63G10L25/78G10L17/00
    • G10L25/63G10L15/22G10L17/00G10L19/018G10L25/78G10L2015/227
    • Systems, methods, and computer-readable storage media are provided for recognizing emotion in audio signals in real-time. An audio signal is detected and a rapid audio fingerprint is computed on a user's computing device. One or more features is extracted from the audio fingerprint and compared with features associated with defined emotions to determine relative degrees of similarity. Confidence scores are computed for the defined emotions based on the relative degrees of similarity and it is determined whether a confidence score for one or more particular emotions exceeds a threshold confidence score. If it is determined that a threshold confidence score for one or more particular emotions is exceeded, the particular emotion or emotions are associated with the audio signal. As desired, various action then may be initiated based upon the emotion/emotions associated with the audio signal.
    • 提供系统,方法和计算机可读存储介质,用于实时地识别音频信号中的情感。 检测音频信号,并在用户的计算设备上计算快速音频指纹。 从音频指纹中提取一个或多个特征,并与与​​所定义的情绪相关联的特征进行比较,以确定相似度。 基于相对的相似度来计算针对所定义情绪的置信度分数,并且确定一个或多个特定情绪的置信度分数是否超过阈值置信度得分。 如果确定超过了一个或多个特定情绪的阈值置信度得分,则特定情绪或情绪与音频信号相关联。 根据需要,可以基于与音频信号相关联的情绪/情绪来启动各种动作。