Guide to Computing for Expressive Music Performance

pp 181-203


Evaluation of Computer Systems for Expressive Music Performance

  • Roberto BresinAffiliated withDepartment of Speech, Music & Hearing, KTH Royal Institute of Technology Email author 
  • , Anders FribergAffiliated withDepartment of Speech, Music & Hearing, KTH Royal Institute of Technology

* Final gross prices may vary according to local VAT.

Get Access


In this chapter, we review and summarize different methods for the evaluation of CSEMPs. The main categories of evaluation methods are (1) comparisons with measurements from real performances, (2) listening experiments, and (3) production experiments. Listening experiments can be of different types. For example, in some experiments, subjects may be asked to rate a particular expressive characteristic (such as the emotion conveyed or the overall expression) or to rate the effect of a particular acoustic cue. In production experiments, subjects actively manipulate system parameters to achieve a target performance. Measures for estimating the difference between performances are discussed in relation to the objectives of the model and the objectives of the evaluation. There will be also a section with a presentation and discussion of the Rencon (Performance Rendering Contest). Rencon is a contest for comparing the expressive musical performances of the same score generated by different CSEMPs. Practical examples from previous works are presented, commented on, and analysed.