An apparatus for generating relations between feature amounts of audio and scene type includes at least one processor and a memory. The memory is operatively coupled to the at least one processor. The processor is configured to set one of the scene types to each of clusters classifying the feature amounts of audio in one or more pieces of content. The processor is also configured to generate a plurality of pieces of learning data, each representative of a feature amount, from among the feature amounts of the audio, that belongs to each cluster and the scene type set for each cluster. The processor is also configured to generate an identification model representative of relations between the feature amounts of audio and the scene types by performing machine learning using the plurality of pieces of learning data.