This paper presents a system that complements the tuner functionality by evaluating the sound quality of a music performer in real-time. It consists of a software tool that computes a score of how well single notes are played with respect to a collection of reference sounds. To develop such a tool we first record a collection of single notes played by professional performers. Then, the collection is annotated by music teachers in terms of the performance quality of each individual sample. From the recorded samples, several audio features are extracted and a machine learning method is used to find the features that best described performance quality according to musician's annotations. An evaluation is carried out to assess the correlation between systems’ predictions and musicians’ criteria. Results show that the system can reasonably predict musicians’ annotations of performance quality.

Authors: Romani Picas, Oriol; Parra Rodriguez, Hector; Dabiri, Dara; Tokuda, Hiroshi; Hariya, Wataru; Oishi, Koji; Serra, Xavier
Affiliations: Universitat Pompeu Fabra, Barcelona, Spain; KORG Inc., Tokyo, Japan(See document for exact affiliation information.)
AES Convention: 138 (May 2015) Paper Number: 9350
Publication Date: May 6, 2015
Subject: Semantic Audio

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.