國立虎尾科技大學 |

Immersive Soundscape Reconstruction Using Contextualized Visual Recognition with Deep Neural Network

Record Type:	Language materials, printed : Monograph/item
Title/Author:	Immersive Soundscape Reconstruction Using Contextualized Visual Recognition with Deep Neural Network/ Mincong Huang.
Author:	Huang, Mincong,
Description:	1 electronic resource (65 pages)
Notes:	Source: Masters Abstracts International, Volume: 82-05.
Contained By:	Masters Abstracts International82-05.
Subject:	Optics. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28025379
ISBN:	9798684653544

Immersive Soundscape Reconstruction Using Contextualized Visual Recognition with Deep Neural Network
Huang, Mincong,

Immersive Soundscape Reconstruction Using Contextualized Visual Recognition with Deep Neural Network [eletronic resource] /Mincong Huang. - 1 electronic resource (65 pages)

Source: Masters Abstracts International, Volume: 82-05.

The use of visual environments to generate corresponding acoustic environments has been of interest in audiovisual fusion research. The scope of works involved are currently limited by user-centered virtual environments with high computational demands. In this work, an immersive soundscape rendering system is developed using machine-learning-based visual recognition techniques. This system utilizes a hand-crafted panoramic image dataset, with their contents identified using pre-trained neural network models for semantic segmentation and object detection. The recognition process extracts spatial information of sound-generating elements in visual environments that are used to position and orient virtual sound sources and locate corresponding contents in pre-assembled audio datasets that consist of both synthetic sounds and pre-recorded audio. This process facilitates a plausible audiovisual rendering schema that could be presented both in binaural format and at the Collaborative-Research Augmented Immersive Virtual Environment Laboratory (CRAIVE-Lab) at Rensselaer Polytechnic Institute. This work intends to situate and enhance audiovisual fusion in human-scale and immersive context.

English

ISBN: 9798684653544Subjects--Topical Terms:

595336
Optics.
Subjects--Index Terms:

Immersion

Immersive Soundscape Reconstruction Using Contextualized Visual Recognition with Deep Neural Network
LDR:02601nam a22004093i 4500 001 1172830
005 20260622113213.5
006 m o d
007 cr|nu||||||||
008 260803s2020 miu||||||m |||||||eng d
020 $a 9798684653544
035 $a (MiAaPQD)AAI28025379
035 $a AAI28025379
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Huang, Mincong, $e author. $3 1503434
245 1 0 $a Immersive Soundscape Reconstruction Using Contextualized Visual Recognition with Deep Neural Network $c Mincong Huang. $h [eletronic resource] /
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2020
300 $a 1 electronic resource (65 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Masters Abstracts International, Volume: 82-05.
500 $a Advisors: Braasch, Jonas Committee members: Xiang, Ning; Krueger, Ted.
502 $b M.S. $c Rensselaer Polytechnic Institute $d 2020.
520 # $a The use of visual environments to generate corresponding acoustic environments has been of interest in audiovisual fusion research. The scope of works involved are currently limited by user-centered virtual environments with high computational demands. In this work, an immersive soundscape rendering system is developed using machine-learning-based visual recognition techniques. This system utilizes a hand-crafted panoramic image dataset, with their contents identified using pre-trained neural network models for semantic segmentation and object detection. The recognition process extracts spatial information of sound-generating elements in visual environments that are used to position and orient virtual sound sources and locate corresponding contents in pre-assembled audio datasets that consist of both synthetic sounds and pre-recorded audio. This process facilitates a plausible audiovisual rendering schema that could be presented both in binaural format and at the Collaborative-Research Augmented Immersive Virtual Environment Laboratory (CRAIVE-Lab) at Rensselaer Polytechnic Institute. This work intends to situate and enhance audiovisual fusion in human-scale and immersive context.
546 $a English
590 $a School code: 0185
650 # 4 $a Optics. $3 595336
650 # 4 $a Artificial intelligence. $3 559380
650 # 4 $a Acoustics. $3 670692
653 # # $a Immersion
653 # # $a Soundscape
653 # # $a Virtual Reality
690 $a 0986
690 $a 0800
690 $a 0752
710 2 # $a Rensselaer Polytechnic Institute. $b Architectural Sciences. $3 1194159
720 1 $a Braasch, Jonas $e degree supervisor.
773 0 # $t Masters Abstracts International $g 82-05.
790 $a 0185
791 $a M.S.
792 $a 2020
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28025379