Sloshing in fuel tanks has become a new source of noise in hybrid and high-end vehicles in the wake of reduced noise from major sources like the engine. It occurs due to the interactions of fluid inside the tank under various driving conditions of the vehicle. Interactions of fluid with the tank walls cause hit noise, and the fluid-fluid interactions cause splash noise. As the generation mechanism is different, the hit and splash noises demand different noise controlling strategies. Thus, identifying these noises during the design stage is important for implementing effective solutions in designing a quieter fuel tank. This paper presents a convolutional neural network (CNN) based methodology for the identification of sloshing noises under different conditions of fill level, excitation, baffle configuration, etc. Data for training and testing the network are collected using a reciprocating test setup, which facilitates the generation of hit and splash noises in a rectangular tank. The identification accuracy of the features learned by CNN is compared with the hand-crafted features using support vector machines. The applicability of the proposed CNN model is tested for practical scenarios like vehicle braking, where different types of sloshing noises occur in quick succession. © 2021 Acoustical Society of America.