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

WO2018138491A1 LOUDSPEAKER PROTECTION SYSTEMS AND METHODS 审中-公开
公开(公告)号：WO2018138491A1
公开(公告)日：2018-08-02
申请号：PCT/GB2018/050196
申请日：2018-01-24
申请人： CIRRUS LOGIC INTERNATIONAL SEMICONDUCTOR LIMITED
发明人： NAPOLI, Roberto , WILLIAMS, Stefan
IPC分类号： H04R3/00 , H04R29/00
CPC分类号： H04R3/007 , G10L25/21 , H03G3/3005 , H04R29/001 , H04R29/003 , H04R2499/11
摘要： A method of thermal protection of a voice coil of a loudspeaker comprises: determining an estimate of a temperature of the voice coil, determining an estimate of a rate of change of the temperature of the voice coil, and determining an estimate of power dissipation in the voice coil. A gain control signal is then generated for modulating a gain applied to an input signal in a signal path between an input terminal and said loudspeaker. The gain control signal is generated as a function of all of the estimate of the temperature of the voice coil, the estimate of the rate of change of the temperature of the voice coil, and the estimate of the power dissipation in the voice coil.

2. 发明申请

WO2017206900A1 声音文件的音质识别方法及装置审中-公开
公开(公告)号：WO2017206900A1
公开(公告)日：2017-12-07
申请号：PCT/CN2017/086575
申请日：2017-05-31
申请人：腾讯科技(深圳)有限公司
发明人：赵伟锋
IPC分类号： G10L25/60
CPC分类号： G10L25/60 , G10L19/0204 , G10L19/173 , G10L19/22 , G10L25/18 , G10L25/21
摘要：声音文件的音质识别方法和装置，音质识别方法包括：将待识别声音文件的格式转换为预先设置的基准音频格式（1022）；对基准音频格式的声音文件进行分帧以及傅立叶变换处理得到声音文件每一帧的频谱（103、104）；根据声音文件每一帧的频谱进行模式匹配，得到对声音文件的初步分类结果（1051）；根据声音文件每一帧的频谱确定声音文件的能量变化点（1052）；以及根据声音文件的初步分类结果及其能量变化点确定声音文件的音质（106）。

3. 发明申请

WO2017131921A1 METHODS AND SYSTEMS FOR PROVIDING CONSISTENCY IN NOISE REDUCTION DURING SPEECH AND NON-SPEECH PERIODS 审中-公开
标题翻译：用于在语音和非语音期间为降低噪音提供一致性的方法和系统
公开(公告)号：WO2017131921A1
公开(公告)日：2017-08-03
申请号：PCT/US2016/069094
申请日：2016-12-29
申请人： KNOWLES ELECTRONICS, LLC
发明人： YEN, Kuan-Chieh
IPC分类号： G10L21/02 , H04R3/00 , G10L21/0232
CPC分类号： G10L21/0216 , G10L21/02 , G10L21/0232 , G10L21/0364 , G10L25/21 , G10L25/93 , G10L2021/02166 , G10L2021/02168 , G10L2025/937 , H04R1/1016 , H04R1/1083 , H04R3/005 , H04R2410/05
摘要： Methods and systems for providing consistency in noise reduction during speech and non-speech periods are provided. First and second signals are received. The first signal includes at least a voice component. The second signal includes at least the voice component modified by human tissue of a user. First and second weights may be assigned per subband to the first and second signals, respectively. The first and second signals are processed to obtain respective first and second full-band power estimates. During periods when the user's speech is not present, the first weight and the second weight are adjusted based at least partially on the first full-band power estimate and the second full-band power estimate. The first and second signals are blended based on the adjusted weights to generate an enhanced voice signal. The second signal may be aligned with the first signal prior to the blending.
摘要翻译：提供了用于在语音和非语音期间降低噪声一致性的方法和系统。接收第一和第二信号。第一信号至少包括语音分量。第二信号至少包括由用户的人体组织修改的语音分量。可以将第一和第二权重分别按每个子带分配给第一和第二信号。处理第一和第二信号以获得相应的第一和第二全频带功率估计。在用户的语音不存在期间，至少部分基于第一全频带功率估计和第二全频带功率估计来调整第一权重和第二权重。第一和第二信号基于调整的权重被混合以生成增强的语音信号。第二个信号可以在混合之前与第一个信号对齐。

4. 发明申请

WO2017078361A1 ELECTRONIC DEVICE AND METHOD FOR RECOGNIZING SPEECH 审中-公开
标题翻译：用于识别语音的电子设备和方法
公开(公告)号：WO2017078361A1
公开(公告)日：2017-05-11
申请号：PCT/KR2016/012427
申请日：2016-11-01
申请人： SAMSUNG ELECTRONICS CO., LTD.
发明人： SHIN, Ki-hoon
IPC分类号： G10L15/08 , G10L15/28 , G06F3/16
CPC分类号： G10L25/84 , G10L15/02 , G10L15/20 , G10L15/26 , G10L21/0208 , G10L21/0232 , G10L21/0272 , G10L25/21 , G10L2021/02166 , G10L2025/783
摘要： An electronic device and a method for recognizing a speech are provided. The method for recognizing a speech by an electronic device includes: receiving sounds generated from a sound source through a plurality of microphones; calculating power values from a plurality of audio signals generated by performing signal processing on each sound input through the plurality of microphones and calculating direction information on the sound source based on the calculated power values and storing the calculated direction information; and performing the speech recognition on a speech section included in the audio signal based on the direction information on the sound source. As a result, the electronic device may correctly detect only a speech section from an audio signal while improving a speech section detection related processing speed.
摘要翻译：提供了一种用于识别语音的电子设备和方法。通过电子设备识别语音的方法包括：通过多个麦克风接收从声源生成的声音; 根据通过对通过所述多个麦克风输入的每个声音执行信号处理而生成的多个音频信号计算功率值，并且基于所计算的功率值计算关于所述声源的方向信息，并且存储所计算的方向信息; 以及基于关于声源的方向信息在包括在音频信号中的语音部分上执行语音识别。结果，电子设备可以在改善语音部分检测相关处理速度的同时正确地从音频信号中仅检测语音部分。

5. 发明申请

WO2016168356A1 ADAPTIVE ARITHMETIC CODING OF AUDIO CONTENT 审中-公开
标题翻译：音频内容的自适应算术编码
公开(公告)号：WO2016168356A1
公开(公告)日：2016-10-20
申请号：PCT/US2016/027362
申请日：2016-04-13
申请人： DOLBY LABORATORIES LICENSING CORPORATION , DOLBY INTERNATIONAL AB
发明人： SUN, Xuejing , SHI, Dong , KLEJSA, Janusz
IPC分类号： G10L19/00 , G10L19/20 , G10L25/78 , G10L25/21 , G10L25/51 , G10L25/18
CPC分类号： G10L19/0017 , G10L19/0204 , G10L19/20 , G10L25/18 , G10L25/21 , G10L25/51 , G10L25/78 , H03M7/4037 , H03M7/6011 , H03M7/6017
摘要： Disclosed is a system and computer program product of encoding audio content and corresponding method. The method includes determining a characteristic of the audio content, the characteristic of the audio content including at least one of a type or a property of the audio content. Also the method includes classifying the audio content based on the characteristic of the audio content and determining probabilities for multiple predefined audio coding symbols associated with the audio content by calculating a probability for each of the audio coding symbols based on the result of the classification, the probability for an audio coding symbol indicating a frequency at which the audio coding symbol occurs in the audio content. Further, the method encoded the audio content based on the audio coding symbols and the corresponding probabilities to obtain a code value, the code value representing a compression coding format of the audio content.
摘要翻译：公开了一种对音频内容进行编码和相应方法的系统和计算机程序产品。该方法包括确定音频内容的特性，音频内容的特征包括音频内容的类型或属性中的至少一个。此外，该方法包括基于音频内容的特性对音频内容进行分类，并且通过基于分类结果计算每个音频编码符号的概率来确定与音频内容相关联的多个预定音频编码符号的概率，表示在音频内容中出现音频编码符号的频率的音频编码符号的概率。此外，该方法基于音频编码符号和相应的概率编码音频内容以获得代码值，代码值表示音频内容的压缩编码格式。

6. 发明申请

WO2016140718A1 METHODS AND APPARATUS FOR REDUCING AUDIO CONFERENCE NOISE USING VOICE QUALITY MEASURES 审中-公开
标题翻译：使用语音质量度量来减少音频会议噪声的方法和装置
公开(公告)号：WO2016140718A1
公开(公告)日：2016-09-09
申请号：PCT/US2015/064413
申请日：2015-12-08
申请人： RAYTHEON COMPANY
发明人： FEMAL, Michael, J.
IPC分类号： G10L25/09 , G10L25/21
CPC分类号： H04M3/568 , G10L25/09 , G10L25/21 , G10L25/78
摘要： Methods and apparatus for monitoring audio quality and controlling noise in telephone conferences. In one example, voice activity detection processing is implemented based on the energy in the audio signal of each channel and the zero crossing rate of the audio signal to differentiate noise from speech. Certain examples further include the use of a voice quality index and activity timer to determine audio quality.
摘要翻译：用于监听电话会议音频质量和控制噪声的方法和装置。在一个示例中，语音活动检测处理基于每个频道的音频信号中的能量和音频信号的过零率来实现，以区分噪声与语音。某些示例进一步包括使用语音质量指标和活动定时器来确定音频质量。

7. 发明申请

WO2016016144A1 APPARATUS AND METHOD FOR GENERATING AN ENHANCED SIGNAL USING INDEPENDENT NOISE-FILLING 审中-公开
标题翻译：使用独立噪声填充生成增强信号的装置和方法
公开(公告)号：WO2016016144A1
公开(公告)日：2016-02-04
申请号：PCT/EP2015/067058
申请日：2015-07-24
申请人： FRAUNHOFER-GESELLSCHAFT ZUR FÖRDERUNG DER ANGEWANDTEN FORSCHUNG E.V.
发明人： DISCH, Sascha , GEIGER, Ralf , NIEDERMEIER, Andreas , NEUSINGER, Matthias , SCHMIDT, Konstantin , WILDE, Stephan , SCHUBERT, Benjamin , NEUKAM, Christian
IPC分类号： G10L19/028 , G10L21/038
CPC分类号： G10L19/028 , G10L19/0204 , G10L21/038 , G10L25/21
摘要： An apparatus for generating an enhanced signal from an input signal (600), wherein the enhanced signal has spectral values for an enhancement spectral region, the spectral values for the enhancement spectral regions not being contained in the input signal (600), comprises a mapper (602) for mapping a source spectral region of the input signal to a target region in the enhancement spectral region, the source spectral region comprising a noise-filling region (302); and a noise filler (604) configured for generating first noise values for the noise-filling region (302) in the source spectral region of the input signal and for generating second noise values for a noise region in the target region, wherein the second noise values are decorrelated from the first noise values or for generating second noise values for a noise region in the target region, wherein the second noise values are decorrelated from first noise values in the source region.
摘要翻译：一种用于从输入信号（600）生成增强信号的装置，其中所述增强信号具有用于增强频谱区域的频谱值，所述增强频谱区域的频谱值不包含在所述输入信号（600）中，包括映射器（602），用于将所述输入信号的源光谱区域映射到所述增强光谱区域中的目标区域，所述源光谱区域包括噪声填充区域（302）; 以及噪声填充器（604），其被配置用于为所述输入信号的源频谱区域中的所述噪声填充区域（302）生成第一噪声值，并且用于产生所述目标区域中的噪声区域的第二噪声值，其中所述第二噪声值从第一噪声值解相关或用于为目标区域中的噪声区域产生第二噪声值，其中第二噪声值与源区域中的第一噪声值相关。

8. 发明申请

WO2016015485A1 音频编码方法及相关装置审中-公开
公开(公告)号：WO2016015485A1
公开(公告)日：2016-02-04
申请号：PCT/CN2015/075645
申请日：2015-04-01
申请人：华为技术有限公司
发明人：刘泽新 , 苗磊
IPC分类号： G10L19/02
CPC分类号： G10L19/22 , G10L19/0204 , G10L19/0208 , G10L19/0212 , G10L19/12 , G10L25/18 , G10L25/21
摘要：一种音频编码方法以及相关装置，该音频编码方法包括：对当前音频帧的时域信号进行时频变换处理以得到上述当前音频帧的频谱系数（101）；获取当前音频帧的编码参考参数（102）；若获取的上述当前音频帧的编码参考参数符合第一参数条件，基于变换码激励编码算法对上述当前音频帧的频谱系数进行编码（103）；若获取的上述当前音频帧的编码参考参数符合第二参数条件，基于高质量变换编码算法对上述当前音频帧的频谱系数进行编码（104）。其中，该音频编码方法以及相关装置有利于提高音频帧编码的编码质量或编码效率。

9. 发明申请

WO2015147362A1 차신호 고주파 신호의 비교법에 의한 음주 판별 방법, 이를 수행하기 위한 기록 매체 및 장치 审中-公开
标题翻译：用于通过差分信号中的高频信号比较确定酒精的方法，以及用于实现其的记录介质和装置
公开(公告)号：WO2015147362A1
公开(公告)日：2015-10-01
申请号：PCT/KR2014/002849
申请日：2014-04-02
申请人： 숭실대학교산학협력단 , (주) 지씨에스씨
发明人： 배명진 , 이상길 , 배성근
IPC分类号： G10L25/51 , G10L25/93
CPC分类号： G10L25/66 , A61B5/4803 , A61B5/4845 , A61B5/7257 , A61B5/7264 , A61B7/00 , G10L25/15 , G10L25/21 , G10L25/30 , G10L25/93
摘要： 음주 판별 방법은, 입력된 음성 신호의 유효 프레임을 검출하는 단계; 유효 프레임의 원신호의 차신호를 검출하는 단계; 차신호의 고속 푸리에 변환을 수행하여 주파수 영역으로 변환하는 단계; 고속 푸리에 변환된 차신호의 고주파 성분들을 검출하는 단계; 및 고주파 성분들 간의 기울기 차이에 기초하여 음주 상태를 판단하는 단계를 포함한다. 이에 따라, 원거리에 있는 운전자 또는 운항자의 음주 여부 및 정도를 파악할 수 있으므로, 음주 운전 또는 운항으로 인한 사고를 예방할 수 있다.
摘要翻译：用于确定酒精使用的方法包括以下步骤：检测输入音频信号中的有效帧; 检测有效帧的原始信号中的差分信号; 对要变换为频域的差分信号执行快速傅里叶变换; 检测经受快速傅立叶变换的差分信号中的高频分量; 并且基于高频分量之间的梯度差来确定酒精使用的状态。因此，本发明可以识别驾驶员或操作者长时间使用酒精的状态和程度，从而可以防止在酒精的影响下驾驶或操作引起的事故。

10. 发明申请

WO2015134579A1 SYSTEM AND METHOD TO CORRECT FOR PACKET LOSS IN ASR SYSTEMS 审中-公开
标题翻译：纠正ASR系统中分组丢失的系统和方法
公开(公告)号：WO2015134579A1
公开(公告)日：2015-09-11
申请号：PCT/US2015/018692
申请日：2015-03-04
申请人： INTERACTIVE INTELLIGENCE GROUP, INC.
发明人： CHELUVARAJA, Srinath , IYER, Ananth Nagaraja , GANAPATHIRAJU, Aravind , WYSS, Felix Immanuel
IPC分类号： G10L15/14
CPC分类号： G10L19/005 , G10L15/02 , G10L15/08 , G10L15/14 , G10L15/20 , G10L25/18 , G10L25/21 , G10L2015/025 , G10L2019/0012
摘要： A system and method are presented for the correction of packet loss in audio in automatic speech recognition (ASR) systems. Packet loss correction, as presented herein, occurs at the recognition stage without modifying any of the acoustic models generated during training. The behavior of the ASR engine in the absence of packet loss is thus not altered. To accomplish this, the actual input signal may be rectified, the recognition scores may be normalized to account for signal errors, and a best-estimate method using information from previous frames and acoustic models may be used to replace the noisy signal.
摘要翻译：提出了一种用于在自动语音识别（ASR）系统中校正音频中的分组丢失的系统和方法。如本文所示，分组丢失校正发生在识别阶段，而不修改在训练期间产生的任何声学模型。因此，在没有丢包的情况下，ASR引擎的行为不会改变。为了实现这一点，实际输入信号可以被纠正，识别分数可以被归一化以考虑信号误差，并且可以使用使用来自先前帧和声学模型的信息的最佳估计方法来代替噪声信号。

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