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

US20140355751A1 Systems and Methods for Echo Reduction 有权
标题翻译：回波减少的系统和方法
公开(公告)号：US20140355751A1
公开(公告)日：2014-12-04
申请号：US14184877
申请日：2014-02-20
申请人： Tencent Technology (Shenzhen) Company Limited
发明人： Xingping Long , Hong Liu , Muyong Cao
IPC分类号： H04R3/02 , H04M1/253
CPC分类号： H04R3/02 , H04B3/231 , H04M9/08 , H04M9/082
摘要： Systems and methods are provided for echo reduction. For example, first audio data associated with a current time unit is obtained, the first audio data being generated by an audio-acquisition device of a receiver based on at least information associated with a first audio signal acquired by the audio-acquisition device and a second audio signal output from an audio-playback device of the receiver, the second audio signal being output from the audio-playback device of the receiver based on at least information associated with second audio data transmitted previously by a sender before the current time unit; third audio data transmitted by the sender during a second time unit preceding the current time unit is obtained; and fourth audio data is obtained by performing echo reduction on the first audio data based on at least information associated with the third audio data.
摘要翻译：提供了回波减少的系统和方法。例如，获得与当前时间单元相关联的第一音频数据，所述第一音频数据由接收机的音频采集设备至少基于与由音频采集设备获取的第一音频信号相关联的信息生成，以及从接收机的音频再现装置输出的第二音频信号，所述第二音频信号至少基于与当前时间单位之前的发送者先前发送的第二音频数据相关联的信息从所述接收机的音频回放装置输出; 获得在当前时间单元之前的第二时间单元期间由发送器发送的第三音频数据; 并且通过至少基于与第三音频数据相关联的信息对第一音频数据执行回波减小来获得第四音频数据。

2. 发明公开

US20240194214A1 TRAINING METHOD AND ENHANCEMENT METHOD FOR SPEECH ENHANCEMENT MODEL, APPARATUS, ELECTRONIC DEVICE, STORAGE MEDIUM AND PROGRAM PRODUCT 审中-公开
公开(公告)号：US20240194214A1
公开(公告)日：2024-06-13
申请号：US18582989
申请日：2024-02-21
申请人： Tencent Technology (Shenzhen) Company Limited
发明人： Xuefei Fang , Dong Yang , Muyong Cao
IPC分类号： G10L21/0324
CPC分类号： G10L21/0324
摘要： A training method and an enhancement method for a speech enhancement model, an apparatus, an electronic device, a storage medium, and a program product are described. A training method for the model may include: invoking the model based on a noisy speech feature of a speech signal, to obtain first predicted mask values in an auditory domain. A first amplitude and first phase of the noisy speech signal, and a second amplitude and second phase of a clean speech signal may then be obtained. A phase difference at each frequency point may be determined based on the phases. The second amplitude corresponding to each frequency point may be corrected based on the phase difference at each frequency point, to obtain a corrected second amplitude corresponding to each frequency point. A loss value is determined, and parameters of the speech enhancement model may be updated based on the loss value.

3. 发明授权

US09626985B2 Audio processing method and apparatus 有权
公开(公告)号：US09626985B2
公开(公告)日：2017-04-18
申请号：US15036926
申请日：2014-10-21
申请人： TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
发明人： Muyong Cao , Junming Li , Xingping Long , Guangfa Li
IPC分类号： G10L21/02 , G10L21/0208 , G10L19/16 , H04J3/06 , H04L12/801 , H04L12/26 , H04N21/439
CPC分类号： G10L21/0208 , G10L19/167 , G10L21/0202 , H04J3/0632 , H04L43/087 , H04L47/10 , H04N21/439 , H04N21/4392 , H04N21/4394
摘要： Audio processing methods and apparatus are provided. An audio processing method may include: receiving audio data packets; buffering the audio data packets to a buffer; reading the audio data packets from the buffer and playing the audio data packets; accumulating an actual total playing time length and a total sampling time length of the audio data packets that currently have been read from the buffer and have been played; and suspending reading and playing, when a sum of sampling time lengths of audio data packets that are buffered and unread in the buffer is less than or equal to a first threshold, until a sum of sampling time lengths of the audio data packets in the buffer that are unread is greater than or equal to a current network jitter estimated value.

4. 发明申请

US20160044527A1 Systems and Methods for Data Transmission 有权
标题翻译：数据传输系统与方法
公开(公告)号：US20160044527A1
公开(公告)日：2016-02-11
申请号：US14918731
申请日：2015-10-21
申请人： Tencent Technology (Shenzhen) Company Limited
发明人： Xingping Long , Xinhai Zeng , Xiaomin Xu , Muyong Cao , Yuanjiang Peng
IPC分类号： H04W28/02 , H04L12/863 , H04L12/26
CPC分类号： H04W28/0236 , H04L1/1642 , H04L1/1838 , H04L1/1858 , H04L43/0829 , H04L43/0864 , H04L47/54
摘要： Systems and methods are provided for data transmission. For example, packet loss is detected based on at least information associated with a first data packet; and in response to packet loss being detected, a packet-retransmission request is sent to a data-transmission terminal and the packet-retransmission request is repeatedly sent to the data-transmission terminal during a retransmission life-cycle associated with the first data packet, the packet-retransmission request including a first identification of the packet-retransmission request.
摘要翻译：提供了数据传输的系统和方法。例如，至少基于与第一数据分组相关联的信息来检测分组丢失; 并且响应于检测到分组丢失，将分组重传请求发送到数据传输终端，并且在与第一数据分组相关联的重传生命周期期间重复发送分组重传请求到数据传输终端，分组重传请求包括分组重传请求的第一标识。

5. 发明授权

US12009004B2 Speech enhancement method and apparatus, electronic device, and computer-readable storage medium 有权
公开(公告)号：US12009004B2
公开(公告)日：2024-06-11
申请号：US17717620
申请日：2022-04-11
申请人： Tencent Technology (Shenzhen) Company Limited
发明人： Xuefei Fang , Xiaochun Cui , Congbing Li , Xiaoyu Liu , Muyong Cao , Tao Yu , Dong Yang , Rongxin Zhou , Wenyan Li
IPC分类号： G10L21/00 , G06N3/04 , G06N3/08 , G10L21/0232 , G10L25/18 , G10L25/30
CPC分类号： G10L21/0232 , G06N3/08 , G10L25/18 , G10L25/30
摘要： Embodiments of this disclosure provide a speech enhancement method and apparatus, an electronic device, and a computer-readable storage medium. The method includes: obtaining a clean speech sample; decomposing the clean speech sample to obtain a first sparse matrix and m base matrices, values in the first sparse matrix being all positive numbers, and m being a positive integer greater than 1; obtaining, according to the first sparse matrix and a weight matrix of a target neural network, state vectors of neurons in a visible layer of the target neural network; and updating the weight matrix according to the state vectors of the neurons in the visible layer and the clean speech sample, to obtain a deep dictionary used for speech enhancement.

6. 发明授权

US09872198B2 Systems and methods for data transmission 有权
公开(公告)号：US09872198B2
公开(公告)日：2018-01-16
申请号：US14918731
申请日：2015-10-21
申请人： Tencent Technology (Shenzhen) Company Limited
发明人： Xingping Long , Xinhai Zeng , Xiaomin Xu , Muyong Cao , Yuanjiang Peng
IPC分类号： H04W28/02 , H04L1/16 , H04L1/18 , H04L12/26 , H04L12/863
CPC分类号： H04W28/0236 , H04L1/1642 , H04L1/1838 , H04L1/1858 , H04L43/0829 , H04L43/0864 , H04L47/54
摘要： Systems and methods are provided for data transmission. For example, packet loss is detected based on at least information associated with a first data packet; and in response to packet loss being detected, a packet-retransmission request is sent to a data-transmission terminal and the packet-retransmission request is repeatedly sent to the data-transmission terminal during a retransmission life-cycle associated with the first data packet, the packet-retransmission request including a first identification of the packet-retransmission request.

7. 发明授权

US09414162B2 Systems and methods for echo reduction 有权
标题翻译：减少回波的系统和方法
公开(公告)号：US09414162B2
公开(公告)日：2016-08-09
申请号：US14184877
申请日：2014-02-20
申请人： Tencent Technology (Shenzhen) Company Limited
发明人： Xingping Long , Hong Liu , Muyong Cao
IPC分类号： H04R3/02 , H04M9/08 , H04B3/23
CPC分类号： H04R3/02 , H04B3/231 , H04M9/08 , H04M9/082
摘要： Systems and methods are provided for echo reduction. For example, first audio data associated with a current time unit is obtained, the first audio data being generated by an audio-acquisition device of a receiver based on at least information associated with a first audio signal acquired by the audio-acquisition device and a second audio signal output from an audio-playback device of the receiver, the second audio signal being output from the audio-playback device of the receiver based on at least information associated with second audio data transmitted previously by a sender before the current time unit; third audio data transmitted by the sender during a second time unit preceding the current time unit is obtained; and fourth audio data is obtained by performing echo reduction on the first audio data based on at least information associated with the third audio data.
摘要翻译：提供了回波减少的系统和方法。例如，获得与当前时间单元相关联的第一音频数据，所述第一音频数据由接收机的音频采集设备至少基于与由音频采集设备获取的第一音频信号相关联的信息生成，以及从接收机的音频再现装置输出的第二音频信号，所述第二音频信号至少基于与当前时间单位之前的发送者先前发送的第二音频数据相关联的信息从所述接收机的音频回放装置输出; 获得在当前时间单元之前的第二时间单元期间由发送器发送的第三音频数据; 并且通过至少基于与第三音频数据相关联的信息对第一音频数据执行回波减小来获得第四音频数据。

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