-
公开(公告)号：US08392198B1
公开(公告)日：2013-03-05
申请号：US12062251
申请日：2008-04-03
申请人： Visar Berisha , Andreas Spanias
发明人： Visar Berisha , Andreas Spanias
IPC分类号： G01L19/00
CPC分类号： G10L19/0204
摘要： A frame is received that has the wideband audio signal. The low band audio signal is encoded to generate an encoded low band signal. The high band signal is analyzed to determine whether the high band signal is perceptually relevant to the low band signal. If the high band signal is not perceptually relevant to the low band signal, the low band signal is encoded and provided in a frame to the decoder without including parameters corresponding to characteristics of the high band signal. If the high band signal is perceptually relevant, the high band signal is encoded to generate an encoded high band signal. The resultant frame that is sent to the decoder will include a combination of the encoded low band signal and the encoded high band signal.
摘要翻译： 接收到具有宽带音频信号的帧。 低频音频信号被编码以产生编码的低频带信号。 分析高频带信号以确定高频带信号是否在感知上与低频信号相关。 如果高频带信号与低频带信号不是感知相关的，则低频带信号被编码并且在帧中提供给解码器，而不包括与高频带信号的特性对应的参数。 如果高频带信号在感知上相关，则对高频带信号进行编码以产生编码的高频带信号。 发送到解码器的结果帧将包括编码的低频带信号和编码的高频带信号的组合。
-
公开(公告)号：US20200043508A1
公开(公告)日：2020-02-06
申请号：US16530304
申请日：2019-08-02
IPC分类号： G10L21/028 , G10L25/24 , G10L25/30 , G06N3/08 , G06N3/04
摘要： Various embodiments of a systems and methods for a triplet network having speaker diarization are disclosed.
-
3.发明申请System and method for satelllite-based transmission of voice signals using an otherwise dedicated wireless channel 有权使用专用无线信道的基于卫星传输语音信号的系统和方法公开(公告)号：US20050053100A1
公开(公告)日：2005-03-10
申请号：US10658435
申请日：2003-09-08
申请人： Glen Abousleman , Damien Budge , Visar Berisha
发明人： Glen Abousleman , Damien Budge , Visar Berisha
CPC分类号： H04B7/18515
摘要： In a wireless communication system (20) configured for default communication of subsectional signals of a first transmit signal (72/73) over multiple wireless channels (46), a signal selector (82) and method (138) detect an intent to convey a voice signal (86) over one of the wireless channels (46) from a handset (58). The signal selector (82) and method (138) prevent communication of one of the subsectional signals (72A) over the wireless channel (46) for a predetermined interval, and enable a transmission attempt of the voice signal (86). When a complete dialed digits sequence is detected within the time interval, the handset (58) is enabled to utilize the wireless channel. However, when a transmission attempt of the voice signal (86) is unsuccessful or when transmission of the voice signal (86) terminates, the signal selector (82) and method (138) restore default communication of subsectional signals of the first transmit signal (72/73).
摘要翻译： 在被配置为通过多个无线信道（46）对第一发射信号（72/73）的子信号进行默认通信的无线通信系统（20）中，信号选择器（82）和方法（138）检测传达 来自手机（58）的无线信道（46）之一上的话音信号（86）。 信号选择器（82）和方法（138）防止通过无线信道（46）通过无线信道（46）之一的子信号（72A）之间的预定间隔进行通信，并使能语音信号（86）的发送尝试。 当在时间间隔内检测到完整的拨号数字序列时，手机（58）被使能以利用无线信道。 然而，当语音信号（86）的发送尝试不成功或当语音信号（86）的发送终止时，信号选择器（82）和方法（138）恢复第一发送信号（83）的子信号的默认通信 72/73）。
-
公开(公告)号：US11152013B2
公开(公告)日：2021-10-19
申请号：US16530304
申请日：2019-08-02
IPC分类号： G10L21/028 , G10L25/24 , G06N3/04 , G06N3/08 , G10L25/30
摘要： Various embodiments of a systems and methods for a triplet network having speaker diarization are disclosed.
-
公开(公告)号：US20230129133A1
公开(公告)日：2023-04-27
申请号：US18047374
申请日：2022-10-18
IPC分类号： G06N3/08
摘要： Hierarchical coarse-grain sparsity for deep neural networks is provided. An algorithm-hardware co-optimized memory compression technique is proposed to compress deep neural networks in a hardware-efficient manner, which is referred to herein as hierarchical coarse-grain sparsity (HCGS). HCGS provides a new long short-term memory (LSTM) training technique which enforces hierarchical structured sparsity by randomly dropping static block-wise connections between layers. HCGS maintains the same hierarchical structured sparsity throughout training and inference; this reduces weight storage for both training and inference hardware systems.
-
6.发明授权公开(公告)号：US09055374B2
公开(公告)日：2015-06-09
申请号：US12822875
申请日：2010-06-24
IPC分类号： H04R29/00
CPC分类号： H04R29/00
摘要： A method and apparatus for determining an auditory pattern associated with an audio segment. An average intensity at each of a first plurality of detector locations on an auditory scale based at least in part on a first plurality of frequency components that describe a signal is determined. A plurality of tonal bands in the audio segment, wherein each tonal band comprises a particular range of detector locations of the first plurality of detector locations is determined. Corresponding strongest frequency components in the tonal bands are determined. A plurality of non-tonal bands is determined, and each non-tonal band is subdivided into multiple sub-bands. Corresponding combined frequency components that are representative of a combined sum of intensities of the first plurality of frequency components that is in a corresponding sub-band are determined. An auditory based on the corresponding strongest frequency components and the corresponding combined frequency components is determined.
摘要翻译： 一种用于确定与音频段相关联的听觉模式的方法和装置。 至少部分地基于描述信号的第一多个频率分量来确定在听觉标尺上的第一多个检测器位置中的每一个处的平均强度。 音频段中的多个音调频带，其中每个音调频带包括第一多个检测器位置的特定范围的检测器位置被确定。 确定音调带中相应最强的频率分量。 确定多个非音调频带，并且每个非音调频带被细分为多个子频带。 确定表示在相应子带中的第一多个频率分量的强度的组合和的相应的组合频率分量。 确定基于相应的最强频率分量和对应的组合频率分量的听觉。
-
7.发明申请公开(公告)号：US20110150229A1
公开(公告)日：2011-06-23
申请号：US12822875
申请日：2010-06-24
IPC分类号： H04R29/00
CPC分类号： H04R29/00
摘要： A method and apparatus for determining an auditory pattern associated with an audio segment. An average intensity at each of a first plurality of detector locations on an auditory scale based at least in part on a first plurality of frequency components that describe a signal is determined. A plurality of tonal bands in the audio segment, wherein each tonal band comprises a particular range of detector locations of the first plurality of detector locations is determined. Corresponding strongest frequency components in the tonal bands are determined. A plurality of non-tonal bands is determined, and each non-tonal band is subdivided into multiple sub-bands. Corresponding combined frequency components that are representative of a combined sum of intensities of the first plurality of frequency components that is in a corresponding sub-band are determined. An auditory based on the corresponding strongest frequency components and the corresponding combined frequency components is determined.
摘要翻译： 一种用于确定与音频段相关联的听觉模式的方法和装置。 至少部分地基于描述信号的第一多个频率分量来确定在听觉标尺上的第一多个检测器位置中的每一个处的平均强度。 音频段中的多个音调频带，其中每个音调频带包括第一多个检测器位置的特定范围的检测器位置被确定。 确定音调带中相应最强的频率分量。 确定多个非音调频带，并且每个非音调频带被细分为多个子频带。 确定表示在相应子带中的第一多个频率分量的强度的组合和的相应的组合频率分量。 确定基于相应的最强频率分量和对应的组合频率分量的听觉。
-
-
-
-
-
-
搜索结果
7 条记录 (耗时 0.014 秒)