Abstract: Automatic performance data of plural channels are read from a memory, these data are interpolated by interpolation data and an automatic performance tone is generated on the basis of the interpolated automatic performance data. The interpolation data can be variably set in accordance with an operation by a player whereby the player's feeling can be reflected freely on the automatic performance in real time performance. Change data for changing the automatic performance data may be stored in a memory and this change data may be selected freely by a selective operation by the player. The selected change data may be variably controlled by an operation by the player. Plural types of change data patterns corresponding to one phrase may be stored and a sequence combination of these change data patterns may be freely set and changed. By these arrangements, an automatic performance which is rich in expression of feeling as in a live performance can be realized.

Abstract: An electronic musical instrument utilizing neural nets comprises parameter input device for inputting a parameter and a neural net device for calculating the parameter. The neural net device is in advance learning therefore, any input parameter results in proper output by interpolation. The instrument further comprises a weighting data memory, the weighting data being provided to the neural net device. The output of the neural net device is interpreted by an interpreter using interpretation knowledge stored in a memory, thereby the output of the neural net device being changed to musical values. Further, the musical values are modified by an output modifier using modification knowledge stored in another memory so as to be accepted musically. The weighting data, the interpretation knowledge and the modification knowledge can be selected by use of selectors, thus use of the selectors expands musical variation.

Abstract: A musical tone parameter generating method and a musical tone generating device of this invention feature that when data inputted by a player is inputted into a neural network as input pattern, the neural network infers the parameters necessary to specify a musical tone wave form to be formed. This makes it possible to get parameters other than those stored in a memory by inferring, which increases variation of the musical tone to be generated.