EXAMPLE-BASED AUDIO INPAINTING

Yoav Schechner; Michael Elad; Yuval Bahat; Yoav Schechner; Michael Elad; Yuval Bahat

EXAMPLE-BASED AUDIO INPAINTING

Yoav Schechner (Inventor), Michael Elad (Inventor), Yuval Bahat (Inventor), Yoav Schechner (Inventor), Michael Elad (Inventor), Yuval Bahat (Inventor)

Technion - Israel Institute of Technology

Research output: Patent

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.

Original language	American English
Patent number	US2015023345
IPC	H04M 7/ 00 A I
Priority date	16/07/14
State	Published - 22 Jan 2015

Cite this

@misc{f12f9b1af53f4da0b5696077fb65f104,

title = "EXAMPLE-BASED AUDIO INPAINTING",

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.",

author = "Yoav Schechner and Michael Elad and Yuval Bahat and Yoav Schechner and Michael Elad and Yuval Bahat",

year = "2015",

month = jan,

day = "22",

language = "American English",

type = "Patent",

note = "US2015023345; H04M 7/ 00 A I",

}

TY - PAT

T1 - EXAMPLE-BASED AUDIO INPAINTING

AU - Schechner, Yoav

AU - Elad, Michael

AU - Bahat, Yuval

AU - Schechner, Yoav

AU - Elad, Michael

AU - Bahat, Yuval

PY - 2015/1/22

Y1 - 2015/1/22

N2 - 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.

AB - 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.

M3 - Patent

M1 - US2015023345

ER -