ITE Technical Group Submission System
Conference Paper's Information
Online Proceedings
[Sign in]
 Go Top Page Go Previous   [Japanese] / [English] 

Paper Abstract and Keywords
Presentation 2023-02-21 14:45
A Note on Improvement of Binauralization Performance Based on Multi-view Learning on 360° Videos
Masaki Yoshida, Ren Togo, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.)
Abstract (in Japanese) (See Japanese page) 
(in English) In this paper, we propose a binaural audio generation method based on multi-view learning using 360◦ videos. Conventionally, learning visually informed binaural audio generation requires ground truth binaural audio. We generate training video data from 360◦ videos and train binaural audio generation. By using 360◦ videos, which allow users to freely manipulate their viewpoints, we can generate multiple video data with different viewing directions. Our approach enables multi-view learning based on videos of the same scene with different viewing directions. Furthermore, we conduct pre-training before binaural audio generation for learning spatial correspondence between the video frame and the audio. In the pre-training, we generate videos in which the gaze direction does not match that of the audio and predict the gap in gaze direction. By using the data generated from 360◦ videos and pre-trained networks, we can improve the accuracy of binaural audio generation.
Keyword (in Japanese) (See Japanese page) 
(in English) Multi-modal learning / Binaural audio / 360° video / Multi-view learning / Pre-training / / /  
Reference Info. ITE Tech. Rep., vol. 47, no. 6, ME2023-33, pp. 65-69, Feb. 2023.
Paper # ME2023-33 
Date of Issue 2023-02-14 (MMS, ME, AIT) 
ISSN Print edition: ISSN 1342-6893    Online edition: ISSN 2424-1970
Download PDF

Conference Information
Conference Date 2023-02-21 - 2023-02-22 
Place (in Japanese) (See Japanese page) 
Place (in English) Hokkaido Univ. 
Topics (in Japanese) (See Japanese page) 
Topics (in English) Image Processing, etc. 
Paper Information
Registration To ME 
Conference Code 2023-02-MMS-ME-AIT-IE-ITS 
Language Japanese 
Title (in Japanese) (See Japanese page) 
Sub Title (in Japanese) (See Japanese page) 
Title (in English) A Note on Improvement of Binauralization Performance Based on Multi-view Learning on 360° Videos 
Sub Title (in English)  
Keyword(1) Multi-modal learning  
Keyword(2) Binaural audio  
Keyword(3) 360° video  
Keyword(4) Multi-view learning  
Keyword(5) Pre-training  
1st Author's Name Masaki Yoshida  
1st Author's Affiliation Hokkaido University (Hokkaido Univ.)
2nd Author's Name Ren Togo  
2nd Author's Affiliation Hokkaido University (Hokkaido Univ.)
3rd Author's Name Takahiro Ogawa  
3rd Author's Affiliation Hokkaido University (Hokkaido Univ.)
4th Author's Name Miki Haseyama  
4th Author's Affiliation Hokkaido University (Hokkaido Univ.)
5th Author's Name  
5th Author's Affiliation ()
6th Author's Name  
6th Author's Affiliation ()
7th Author's Name  
7th Author's Affiliation ()
8th Author's Name  
8th Author's Affiliation ()
9th Author's Name  
9th Author's Affiliation ()
10th Author's Name  
10th Author's Affiliation ()
11th Author's Name  
11th Author's Affiliation ()
12th Author's Name  
12th Author's Affiliation ()
13th Author's Name  
13th Author's Affiliation ()
14th Author's Name  
14th Author's Affiliation ()
15th Author's Name  
15th Author's Affiliation ()
16th Author's Name  
16th Author's Affiliation ()
17th Author's Name  
17th Author's Affiliation ()
18th Author's Name  
18th Author's Affiliation ()
19th Author's Name  
19th Author's Affiliation ()
20th Author's Name  
20th Author's Affiliation ()
Speaker Author-1 
Date Time 2023-02-21 14:45:00 
Presentation Time 15 minutes 
Registration for ME 
Paper # MMS2023-13, ME2023-33, AIT2023-13 
Volume (vol) vol.47 
Number (no) no.6 
Page pp.65-69 
Date of Issue 2023-02-14 (MMS, ME, AIT) 

[Return to Top Page]

[Return to ITE Web Page]

The Institute of Image Information and Television Engineers (ITE), Japan