An Algorithm for Audio Key Finding
نویسنده
چکیده
An algorithm for audio key finding that participated in the 2005 Music Information Retrieval Evaluation Exchange (MIREX 2005) is presented. This algorithm takes a sound file that contains polyphonic audio as input and outputs a key estimate for this file. It is designed to operate on short fragments of audio taken from the beginnings of musical works. The algorithm consists of three stages: chroma template calculation, chroma summary calculation and overall key estimation. MIREX evaluation results are given with a breakdown of correctly identified keys and perfect fifth, relative major/minor and parallel major/minor errors. This algorithm produced the highest composite percentage score by a small margin among participating algorithms.
منابع مشابه
Creating Ground Truth for Audio Key Finding: When the Title Key May Not Be the Key
In this paper, we present an effective and efficient way to create an accurately labeled dataset to advance audio key finding research. The MIREX audio key finding contest has been held twice using classical compositions for which the key is designated in the title. The problem with this accepted practice is that the title key may not be the perceived key in the audio excerpt. To reduce manual ...
متن کاملFuzzy Analysis in Pitch-Class Determination for Polyphonic Audio Key Finding
This paper presents a fuzzy analysis technique for pitch class determination that improves the accuracy of key finding from audio information. Errors in audio key finding, typically incorrect assignments of closely related keys, commonly result from imprecise pitch class determination and biases introduced by the quality of the sound. Our technique is motivated by hypotheses on the sources of a...
متن کاملAudio Key Finding Using Faceg: Fuzzy Analysis with the Ceg Algorithm
Our key finding system consists of a series of O(n) realtime algorithms for determining key from polyphonic audio. The system comprises of two main parts as shown in Figure 1 [1]. The first part (the upper dashed box) generates pitch class information from audio using the standard FFT and a fuzzy analysis technique. The second component (the lower dashed box) uses the pitch class information to...
متن کاملThe Kusc Classical Music Dataset for Audio Key Finding
In this paper, we present a benchmark dataset based on the KUSC classical music collection and provide baseline key-finding comparison results. Audio key finding is a basic music information retrieval task; it forms an essential component of systems for music segmentation, similarity assessment, and mood detection. Due to copyright restrictions and a labor-intensive annotation process, audio ke...
متن کاملTonal Similarity from Audio Using a Template Based Attractor Model
A model that calculates similarity of tonal evolution among pieces in an audio database is presented. The model employs a template based key finding algorithm. This algorithm is used in a sliding window fashion to obtain a sequence of tonal center estimates that delineate the trajectory of tonal evolution in tonal space. A chroma based representation is used to capture tonality information. Tem...
متن کامل