Wine produced countries in European Union categorize quality of wine as three classes by subjective judgements (called as "Appellation" in French) like taste, land of producer, type of grape seed and so on. In order to evaluate those wine quality, unsupervised machine learning with measured optical and chemical data of wine enables to categorize those 3 subjective classes at high accuracies. With those "A.I. Sommelier" techniques, vacuum cleaner sounds are categorized with psychoacoustic parameters and then modeling by image recognition AI of sFFT images correlate with annoyance rating at high rate. Although unsupervised machine learning technique is uncommon, it shows unsupervised machine learning technique is useful for sound quality evaluation