Vocal Competence based Karaoke Recommendation: A Maximum-Margin Joint Model


In online karaoke, the decision process in choosing a song is different from that in music radio, because users usually prefer songs that meet their vocal competence besides their tastes. Traditional music recommendation methods typically model users' personalized preference for songs in terms of content and style. However, this can be improved by considering the degree of matching the vocal competence (e.g. pitch, volume, and rhythm) of users to the vocal requirements of songs. To this end, in this paper, we develop a karaoke recommender system by incorporating vocal competence. Along this line, we propose a joint modeling method named CBNTF by exploiting the mutual enhancement between non-negative tensor factorization (NTF) and support vector machine (SVM). Specifically, we first extract vocal (i.e., pitch, volume, and rhythm) ratings of a user for a song from his/her singing records. Since these vocal ratings encode users' vocal competence from three aspects, we treat these vocal ratings as a tensor, exploit an NTF method, and learn the latent features of users' vocal metrics. These factorized features are simultaneously fed into an SVM classifier and then we use the trained classifier to predict the overall rating of a user with respect to a song. In addition, we propose an enhanced objective function to exploit the mutual enhancement between NTF and SVM, and devise an effective method to solve this objective as a coupled least-squares optimization problem via a maximum margin framework. With the estimated model, we compute the similarity between users and songs in terms of pitch, volume and rhythm and recommend songs to users. Finally, we conduct extensive experiments with real-world online karaoke data. The results demonstrate the effectiveness of our method.

Meeting Name

16th SIAM International Conference on Data Mining, SDM 2016 (2016: May 5-7, Miami, FL)


Computer Science


This research was partially supported by grants from the National Science Foundation for Distinguished Young Scholars of China (Grant No. 61325010), the Science and Technology Program for Public Wellbeing (Grant No. 2013GS340302) and the Fundamental Research Funds for the Central Universities of China (Grant No. WK2350000001). Also, it was supported in part by Natural Science Foundation of China (71329201).

Keywords and Phrases

Data mining; Factorization; Least squares approximations; Optimization; Support vector machines; Tensors; Decision process; Degree of matching; Karaoke; Least-squares optimization; Music recommendation; Objective functions; Singing competence; Tensor factorization; Recommender systems; Karaoke-song recommendation; Non-negative tensor factorization

International Standard Book Number (ISBN)


International Standard Serial Number (ISSN)

2167-0102 ; 2167-0099

Document Type

Article - Conference proceedings

Document Version


File Type





© 2016 Society for Industrial and Applied Mathematics Publications, All rights reserved.