Mirex 2011 Ams - Audio Similarity via Metric Learning

نویسندگان

  • Brian McFee
  • Gert Lanckriet
چکیده

Our submissions (ML1, ML2, ML3) to the Audio Music Similarity (AMS) task are based upon learning an optimal distance metric over vector quantized MFCC histograms. ML1 is optimized to predict similarity derived from a collaborative filter; ML2 is optimized to predict genre similarity; ML3 is an unsupervised baseline which uses a native distance metric. This abstract details the system architecture and parameter settings.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Mirex 2011 - Ams Task: Melody Variation Patterns for Audio Music Similarity

The dynamics of the melodic line is a crucial feature for the temporal variability of the tonal content of a song, and it determines its characteristic mood pattern. A method based on the measure of the variation of the pitch over the song time is proposed as a tool to characterize the music similarity. The pitch-variation vs. time matrices of each of the analyzed song are compared to achieve a...

متن کامل

Mirex 2011 - Ams Task: Multi Descriptor Based Algorithm

A method for the estimation of music similarity based on a combination of timbre, rhythm and tonal content of the songs, is presented in this report. The rhythm is estimated by evaluating the frequency distribution of the tempo pattern of the songs, while the tonal content is estimated by the calculation of an averaged chroma profile of the song. The algorithm is proposed to be submitted to the...

متن کامل

Mirex 2011 - Ams Task: Mfcc/variogram Based Algorithm

A method for the estimation of music similarity based on the use of the standardized variogram as clustering algorithm for Mel Frequency Cepstral Coefficients, is detailed in this report. The standardized variogram is used for the compression of the information of MFCCs. The algorithm is submitted to the Audio Music Similarity task of MIREX 2011, in occasion of the 12th ISMIR Conference.

متن کامل

Submission to Mirex Ams Task 2011 – Sparse Coding Similarity Learning Method

This paper describes our submissions to the MIREX 2011 audio music similarity and retrieval task. The proposed method is based on a machine learning technique – sparse coding (SC). The music similarity is not directly obtained from computed distance measures on audio contents, instead, we predict a higher level similarity scores to match the listener’s subjective perceptions based on these dist...

متن کامل

Submission to Mirex 2011 Genre Classification and Audio Similarity Tasks

In this submission, audio features that approximate timbre, rhythm and tempo are used for genre classification and music similarity estimation. This abstract describes the feature set, distance computation method, and classifier model used for the submitted algorithms.

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2011