Audio Cover Song Identification: MIREX 2006-2007 Results and Analyses

نویسندگان

  • J. Stephen Downie
  • Mert Bay
  • Andreas F. Ehmann
  • M. Cameron Jones
چکیده

This paper presents analyses of the 2006 and 2007 results of the Music Information Retrieval Evaluation eXchange (MIREX) Audio Cover Song Identification (ACS) tasks. The Music Information Retrieval Evaluation eXchange (MIREX) is a community-based endeavor to scientifically evaluate music information retrieval (MIR) algorithms and techniques. The ACS task was created to motivate MIR researchers to expand their notions of similarity beyond acoustic similarity to include the important idea that musical works retain their identity notwithstanding variations in style, genre, orchestration, rhythm or melodic ornamentation, etc. A series of statistical analyses were performed that indicate significant improvements in this domain have been made over the course of 2006-2007. Post-hoc analyses reveal distinct differences between individual systems and the effects of certain classes of queries on performance. This paper discusses some of the techniques that show promise in this research domain

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

The Mtg Submission to Mirex 2008 Audio Cover Song Identification Task

This is an extended abstract that overviews our cover song identification system as submitted to the MIREX 2008 Audio Cover Song Identification task. The system is developed from our 2007 MIREX submission but including some important modifications and parameter tuning. For time reasons, the present document is just a very early draft version. Further versions will be available soon.

متن کامل

A Cover Song Identification System Based on Sequences of Tonal Descriptors

The present paper corresponds to the extended abstract of a system for cover version identification submitted to the Audio Cover Song task in the context of the Music Information Retrieval Evaluation eXchange (MIREX) 2007. The proposed algorithm extracts sequences of tonal descriptors from audio recordings and uses them to compute a similarity measure between two musical pieces.

متن کامل

Improving Binary Similarity and Local Alignment for Cover Song Detection

This is an extended abstract that overviews our cover song detection system as submitted to the MIREX 2008 audio cover song identification task. The system is developed starting from our 2007 submission but includes some important modifications and parameter tuning. Our system obtains the best results in all evaluation measures considered and its accuracy is proved to be statistically significa...

متن کامل

A Chroma-based Tempo-insensitive Distance Measure for Cover Song Identification

In the context of music, a cover version is a remake of a song, often with significant stylistic variation. In this paper we describe a distance measure between sampled audio files that is designed to be insensitive to instrumentation, time shift, temporal scaling and transpositions. The algorithm was submitted to the Music Information Retrieval eXchange (MIREX) 2007 audio cover song identifica...

متن کامل

Cover Song Retrieval by Cross Recurrence Quantification and Unsupervised Set Detection

This extended abstract briefly outlines our submission to the audio cover song identification task run inside the 2009 music information retrieval evaluation exchange (MIREX). We very briefly introduce cover song identification, give an overview of the submitted system, and comment on the evaluation procedure (specially on the used music collections) and the achieved results. As the submission ...

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 2008