-
公开(公告)号：US20150023345A1
公开(公告)日：2015-01-22
申请号：US14332913
申请日：2014-07-16
Inventor： Yoav Schechner , Michael Elad , Yuval Bahat
IPC: H04M7/00
CPC classification number: G10L19/005 , G10L15/02 , G10L19/0212
Abstract: A method for packet loss concealment, comprising: continuously receiving a digital audio stream; extracting audio features from the digital audio stream while the digital audio stream is unharmed; and upon detecting a gap in the digital audio stream, filling the gap with one or more previous segments of the digital audio stream, wherein said filling is based on a matching of the one or more of the extracted audio features with one or more audio features adjacent to the gap.
Abstract translation: 一种用于分组丢失隐藏的方法，包括：连续接收数字音频流; 在数字音频流不受干扰的情况下从数字音频流中提取音频特征; 并且在检测到所述数字音频流中的间隙时，用所述数字音频流的一个或多个先前段填充所述间隙，其中所述填充基于所提取的一个或多个所述音频特征与一个或多个音频特征 毗邻差距。
-
公开(公告)号：US20140368700A1
公开(公告)日：2014-12-18
申请号：US14301676
申请日：2014-06-11
Inventor： Dana Segev , Yoav Schechner , Michael Elad
CPC classification number: G10L21/0208 , G10L15/25 , G10L25/57 , G10L2021/02087 , H04N21/439
Abstract: A method for cross-modal signal denoising, the method comprising using at least one hardware processor for: providing a first multi-modal signal comprising at least two relatively clear modalities; correlating features exhibited simultaneously in the at least two relatively clear modalities of the first multi-modal signal; providing a second multi-modal signal comprising at least one relatively noisy modality and at least one relatively clear modality; and denoising the at least one relatively noisy modality of the second multi-modal signal by associating between (a) features exhibited in the at least one relatively noisy modality of the second multi-modal signal and (b) the features of the first multi-modal signal.
Abstract translation: 一种用于交叉模态信号去噪的方法，所述方法包括使用至少一个硬件处理器：提供包括至少两个相对清晰模态的第一多模态信号; 在第一多模态信号的至少两个相对清晰的模态中同时呈现的相关特征; 提供第二多模式信号，其包括至少一个相对较嘈杂的模态和至少一个相对清晰的模态; 以及通过在（a）在所述第二多模态信号的所述至少一个相对噪声模态中展现的特征与（b）所述第一多模式信号的特征之间的关联来去噪所述第二多模态信号的所述至少一个相对噪声模态; 模态信号。
-
公开(公告)号：US09583111B2
公开(公告)日：2017-02-28
申请号：US14332913
申请日：2014-07-16
Inventor： Yoav Schechner , Michael Elad , Yuval Bahat
IPC: H04M7/00 , G10L19/005 , G10L15/02 , G10L19/02
CPC classification number: G10L19/005 , G10L15/02 , G10L19/0212
Abstract: A method for packet loss concealment, that includes: continuously receiving a digital audio stream; extracting audio features from the digital audio stream while the digital audio stream is unharmed; and upon detecting a gap in the digital audio stream, filling the gap with one or more previous segments of the digital audio stream, wherein the filling is based on a matching of the one or more of the extracted audio features with one or more audio features adjacent to the gap.
Abstract translation: 一种用于分组丢失隐藏的方法，包括：连续接收数字音频流; 在数字音频流不受干扰的情况下从数字音频流中提取音频特征; 并且在检测到所述数字音频流中的间隙时，用所述数字音频流的一个或多个先前段填充所述间隙，其中所述填充基于所提取的一个或多个所述音频特征与一个或多个音频特征 毗邻差距。
-
公开(公告)号：US09576587B2
公开(公告)日：2017-02-21
申请号：US14301676
申请日：2014-06-11
Inventor： Dana Segev , Yoav Schechner , Michael Elad
IPC: G10L21/0208 , H04N21/439 , G10L25/57 , G10L15/25
CPC classification number: G10L21/0208 , G10L15/25 , G10L25/57 , G10L2021/02087 , H04N21/439
Abstract: A method for cross-modal signal denoising, the method comprising using at least one hardware processor for: providing a first multi-modal signal comprising at least two relatively clear modalities; correlating features exhibited simultaneously in the at least two relatively clear modalities of the first multi-modal signal; providing a second multi-modal signal comprising at least one relatively noisy modality and at least one relatively clear modality; and denoising the at least one relatively noisy modality of the second multi-modal signal by associating between (a) features exhibited in the at least one relatively noisy modality of the second multi-modal signal and (b) the features of the first multi-modal signal.
Abstract translation: 一种用于交叉模态信号去噪的方法，所述方法包括使用至少一个硬件处理器：提供包括至少两个相对清晰模态的第一多模态信号; 在第一多模态信号的至少两个相对清晰的模态中同时呈现的相关特征; 提供第二多模式信号，其包括至少一个相对较嘈杂的模态和至少一个相对清晰的模态; 以及通过在（a）在所述第二多模态信号的所述至少一个相对噪声模态中展现的特征与（b）所述第一多模式信号的特征之间的关联来去噪所述第二多模态信号的所述至少一个相对噪声模态; 模态信号。
-
-
-
Search Results
4
records
(took 0.019 seconds)
