Music Recommendation Based on Feature Similarity

Abstract

As the information of online music resources continues to grow, it becomes more and more difficult for users to find their favorite music. Accurate and efficient music recommendation is very important. Music recommendation is a research hotspot in the field of speech processing. Calculate the mel frequency cepstral coefficient (MFCC) feature quantity by analyzing the characteristics of music content. Then, the feature quantities are clustered to compress the music feature values. Finally, the distance metric function is used to calculate the similarity between all music in the feature value database of the searched music. The closer the distance is, the higher the similarity is. According to the similarity, we can get the result of recommendation. The method recommended results have higher accuracy in experiments and provides an idea for music recommendations when user data is missing.