Abstract
Hardness is the most commonly searched timbral attribute within freesound.org, a commonly used online sound effect repository. A perceptual model of hardness was developed to enable the automatic generation of metadata to facilitate hardness-based filtering or sorting of search results. A training dataset was collected of 202 stimuli with 32 sound source types, and perceived hardness was assessed by a panel of listeners. A multilinear regression model was developed on six features: maximum bandwidth, attack centroid, midband level, percussive-to-harmonic ratio, onset strength, and log attack time. This model predicted the hardness of the training data with R 2 = 0.76. It predicted hardness within a new dataset with R 2 = 0.57, and predicted the rank order of individual sources perfectly, after accounting for the subjective variance of the ratings. Its performance exceeded that of human listeners.
Highlights
IntroductionMany online sound effects repositories exist, such as freesound.org, freeSFX.co.uk, and zapsplat
Many online sound effects repositories exist, such as freesound.org, freeSFX.co.uk, and zapsplat.com, where users can upload sounds to be hosted under a Creative Commons (CC) licence
The performance of listeners was assessed by examining the inter-subject agreement, intra-subject consistency, and Tucker-1 correlation loadings [28,29]
Summary
Many online sound effects repositories exist, such as freesound.org, freeSFX.co.uk, and zapsplat. Com, where users can upload sounds to be hosted under a Creative Commons (CC) licence. Commons project is aimed at promoting the creative reuse of CC-licensed audio content. One method of encouraging reuse is to make it easier for users to search for desired sound effects. Most online sound effect repositories employ some form of keyword searching—matching user search queries to titles and/or tags that uploaders have manually ascribed to the sounds. The ability to find a desired sound effect is limited by the quality and quantity of the user-supplied metadata, which may be sparse or inconsistent. Some curated repositories provide technical metadata, such as sample rate and bit depth, or musical descriptors, such as tempo or genre
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
