Cover Song Identification Based on Similarity Fusion
نویسنده
چکیده
We describe a similarity fusion based cover song identification scheme. The Harmonic Pitch Class Profile (HPCP) is chosen as the musical descriptor. First, the similarity between HPCP descriptors of two songs are obtained based on Qmax function and Dmax function, respectively. Then these two similarities are fused via Similarity Network Fusion (SNF) technique, which was originally proposed for combining different kernels for predicting drug-target interactions. Finally, the fused similarity is used to identify the cover versions.
منابع مشابه
Two-layer similarity fusion model for cover song identification
Various musical descriptors have been developed for Cover Song Identification (CSI). However, different descriptors are based on various assumptions, designed for representing distinct characteristics of music, and often differ in scale and noise level. Therefore, a single similarity function combined with a specific descriptor is generally not able to describe the similarity between songs comp...
متن کاملEarly MFCC and HPCP Fusion for Robust Cover Song Identification
While most schemes for automatic cover song identification have focused on note-based features such as HPCP and chord profiles, a few recent papers surprisingly showed that local self-similarities of MFCC-based features also have classification power for this task. Since MFCC and HPCP capture complementary information, we design an unsupervised algorithm that combines normalized, beatsynchronou...
متن کاملAudio Cover Song Identification using Convolutional Neural Network
In this paper, we propose a new approach to cover song identification using a CNN (convolutional neural network). Most previous studies extract the feature vectors that characterize the cover song relation from a pair of songs and used it to compute the (dis)similarity between the two songs. Based on the observation that there is a meaningful pattern between cover songs and that this can be lea...
متن کاملCover Song Identification Based on Data Compression
We present a system for cover song identification. Our approach combines chord sequence estimation with a similarity metric called normalized compression distance.
متن کاملAssessing the results of a cover song identification system with coverSSSSearch
The automatic identification of cover songs, i.e. versions of the same underlying musical piece, is interesting from multiple points of view and, therefore, many approaches for that specific purpose have been proposed [1]. In the present demo we assess the output of a cover song similarity system through the coverSSSSearch graphical user interface (GUI). Our system is primarily based on the sim...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2016