A real-time system for measuring sound goodness in instrumental sounds

TitleA real-time system for measuring sound goodness in instrumental sounds
Publication TypeConference Paper
Year of Publication2015
Conference NameAES 138th Convention
AuthorsRomaní Picas, O., Parra Rodriguez H., Dabiri D., Tokuda H., Hariya W., Oishi K., & Serra X.
Conference Start Date07/05/2015
Conference LocationWarsaw, Poland
AbstractThis paper presents a system that complements the functionality of a typical tuner 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 fi rst 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 and 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.
preprint/postprint documenthttp://hdl.handle.net/10230/32131