-
公开(公告)号:US10014002B2
公开(公告)日:2018-07-03
申请号:US15792566
申请日:2017-10-24
申请人: Red Pill VR, Inc.
IPC分类号: H04R5/00 , G10L25/18 , G10L25/30 , G10L21/028 , G06F3/16
CPC分类号: G10L25/18 , G06F3/165 , G10L21/0272 , G10L21/028 , G10L21/0308 , G10L25/30
摘要: Methods and systems for audio source separation in real-time are described. In an embodiment, the present disclosure describes reading and decoding an audio source into PCM samples, fragmenting Pulse Code Modulation (PCM) samples into fragments, transforming fragments into spectrograms, performing audio source separation using a deep neural network (DNN) to generate an estimated magnitude spectrogram of the component(s) of the audio source, reconstructing the estimated time domain component signals, and streaming the component signals to a playback engine. In an embodiment, a semantic equalizer graphical user allows for real-time mixing of individual component signals.
-
公开(公告)号:US10325615B2
公开(公告)日:2019-06-18
申请号:US15837839
申请日:2017-12-11
申请人: Red Pill VR, Inc
IPC分类号: G10L25/18 , G06F3/0484 , G06F3/16 , G10L21/028 , G10L21/14 , H04S5/00 , G10L21/0272
摘要: Methods and systems for audio source separation in real-time are described. In an embodiment, the present disclosure describes reading and decoding an audio source into PCM samples, fragmenting Pulse Code Modulation (PCM) samples into fragments, transforming fragments into spectrograms, performing audio source separation using a training database that includes a training dictionary and non-negative matrix factorization (NMF) to generate a set of component signals, and streaming the component signals to a playback engine. In an embodiment, a semantic equalizer graphical user allows for fading of individual component signals.
-
公开(公告)号:US20180122403A1
公开(公告)日:2018-05-03
申请号:US15792566
申请日:2017-10-24
申请人: Red Pill VR, Inc.
IPC分类号: G10L25/18 , G10L21/028 , G10L25/30
CPC分类号: G10L25/18 , G06F3/165 , G10L21/0272 , G10L21/028 , G10L21/0308 , G10L25/30
摘要: Methods and systems for audio source separation in real-time are described. In an embodiment, the present disclosure describes reading and decoding an audio source into PCM samples, fragmenting Pulse Code Modulation (PCM) samples into fragments, transforming fragments into spectrograms, performing audio source separation using a deep neural network (DNN) to generate an estimated magnitude spectrogram of the component(s) of the audio source, reconstructing the estimated time domain component signals, and streaming the component signals to a playback engine. In an embodiment, a semantic equalizer graphical user allows for real-time mixing of individual component signals.
-
公开(公告)号:US20180047372A1
公开(公告)日:2018-02-15
申请号:US15672482
申请日:2017-08-09
申请人: Red Pill VR, Inc.
发明人: Laurent Scallie , Alejandro Koretzky , Karthiek Reddy Bokka , Naveen Sasalu Rajashekharappa , Luis Daniel Bernal
IPC分类号: G10H1/00 , G06F3/0481
CPC分类号: G10H1/0008 , G06F3/04815 , G06F3/04847 , G10H1/0025 , G10H1/0066 , G10H1/0091 , G10H2210/026 , G10H2210/051 , G10H2210/066 , G10H2210/105 , G10H2220/005 , G10H2220/116 , G10H2220/131 , G10H2240/085
摘要: Techniques for generating a virtual music experience. The techniques include source separating an arbitrary digital audio input into a plurality of source-separated tracks. Sets of music features are determined from the plurality of source-separated tracks and provided to a video presentation system at a video frame rate of the video presentation system. The providing the sets of music features to the video presentation system causes the video presentation system to animate one or more graphical assets based on the provided sets of music features.
-
公开(公告)号:US10325580B2
公开(公告)日:2019-06-18
申请号:US15672482
申请日:2017-08-09
申请人: Red Pill VR, Inc
发明人: Laurent Scallie , Alejandro Koretzky , Karthiek Reddy Bokka , Naveen Sasalu Rajashekharappa , Luis Daniel Bernal
IPC分类号: G10H1/00 , G06F3/0481 , G06F3/0484
摘要: Techniques for generating a virtual music experience. The techniques include source separating an arbitrary digital audio input into a plurality of source-separated tracks. Sets of music features are determined from the plurality of source-separated tracks and provided to a video presentation system at a video frame rate of the video presentation system. The providing the sets of music features to the video presentation system causes the video presentation system to animate one or more graphical assets based on the provided sets of music features.
-
公开(公告)号:US20180114537A1
公开(公告)日:2018-04-26
申请号:US15837839
申请日:2017-12-11
申请人: Red Pill VR, Inc.
IPC分类号: G10L25/18 , G06F3/0484 , G06F3/16 , G10L21/14 , H04S5/00 , G10L21/028
CPC分类号: G10L25/18 , G06F3/04847 , G06F3/165 , G10L21/0272 , G10L21/028 , G10L21/14 , H04S5/00 , H04S2420/07
摘要: Methods and systems for audio source separation in real-time are described. In an embodiment, the present disclosure describes reading and decoding an audio source into PCM samples, fragmenting Pulse Code Modulation (PCM) samples into fragments, transforming fragments into spectrograms, performing audio source separation using a training database that includes a training dictionary and non-negative matrix factorization (NMF) to generate a set of component signals, and streaming the component signals to a playback engine. In an embodiment, a semantic equalizer graphical user allows for fading of individual component signals.
-
公开(公告)号:US09842609B2
公开(公告)日:2017-12-12
申请号:US15434419
申请日:2017-02-16
申请人: Red Pill VR, Inc.
IPC分类号: H04R5/00 , G10L25/18 , G06F3/16 , G10L21/028 , G06F3/0484 , G10L21/14 , H04S5/00
CPC分类号: G10L25/18 , G06F3/04847 , G06F3/165 , G10L21/0272 , G10L21/028 , G10L21/14 , H04S5/00 , H04S2420/07
摘要: Methods and systems for audio source separation in real-time are described. In an embodiment, the present disclosure describes reading and decoding an audio source into PCM samples, fragmenting Pulse Code Modulation (PCM) samples into fragments, transforming fragments into spectrograms, performing audio source separation using a training database that includes a training dictionary and non-negative matrix factorization (NMF) to generate a set of component signals, and streaming the component signals to a playback engine. In an embodiment, a semantic equalizer graphical user allows for fading of individual component signals.
-
公开(公告)号:US20170236531A1
公开(公告)日:2017-08-17
申请号:US15434419
申请日:2017-02-16
申请人: Red Pill VR, Inc.
IPC分类号: G10L25/18 , H04S5/00 , G06F3/0484 , G10L21/14 , G06F3/16 , G10L21/028
CPC分类号: G10L25/18 , G06F3/04847 , G06F3/165 , G10L21/0272 , G10L21/028 , G10L21/14 , H04S5/00 , H04S2420/07
摘要: Methods and systems for audio source separation in real-time are described. In an embodiment, the present disclosure describes reading and decoding an audio source into PCM samples, fragmenting Pulse Code Modulation (PCM) samples into fragments, transforming fragments into spectrograms, performing audio source separation using a training database that includes a training dictionary and non-negative matrix factorization (NMF) to generate a set of component signals, and streaming the component signals to a playback engine. In an embodiment, a semantic equalizer graphical user allows for fading of individual component signals.
-
-
-
-
-
-
-