Recent research projects have attempted to realize high realism of reproduced sound fields. We propose an innovative method, an automatic scene discrimination, for a user-centric rendering of enhanced realism in the home theater application. The method categorizes various scenes of movie contents based on their audio characteristics, and applies a pre-determined signal processing for each category in real-time. The training model was able to classified new movie contents with a 71% correct ratio. Listeners reported that this scene-based adaptive sound processing bring higher realism.

Authors: Yuyama, Yuta; Kim, Sungyoung; Okumura, Hiraku
Affiliations: Yamaha Corporation, Shizuoka, Japan; Rochester Institute of Technology, Rochester, NY, USA(See document for exact affiliation information.)
AES Conference: 2018 AES International Conference on Spatial Reproduction - Aesthetics and Science (July 2018)
Paper Number: EB1-6
Publication Date: July 30, 2018
Session Subject: Sound Field Reproduction; Multichannel Audio; Home Theater System; Scene Classification; Machine-Learning; SVM; Feature-Extraction

Click to purchase paper as a non-member or you can login as an AES member to see more options.

No AES members have commented on this paper yet.

Subscribe to this discussion

To be notified of new comments on this paper you can subscribe to this RSS feed. Forum users should login to see additional options.

Start a discussion!

If you would like to start a discussion about this paper and are an AES member then you can login here:
Username:
Password:

If you are not yet an AES member and have something important to say about this paper then we urge you to join the AES today and make your voice heard. You can join online today by clicking here.