Abstract-We present a computer audition system that can both annotate novel audio tracks with semantically meaningful words and retrieve relevant tracks from a database of unlabeled audio content given a text-based query. We consider the related tasks of content-based audio annotation and retrieval as one supervised multiclass, multilabel problem in which we model the joint probability of acoustic features and words. We collect a data set of 1700 human-generated annotations that describe 500 Western popular music tracks. For each word in a vocabulary, we use this data to train a Gaussian mixture model (GMM) over an audio feature space. We estimate the parameters of the model using the weighted mixture hierarchies expectation maximization algorithm. This algorithm is more scalable to large data sets and produces better density estimates than standard parameter estimation techniques. The quality of the music annotations produced by our system is comparable with the performance of humans on the same task. Our "query-by-text" system can retrieve appropriate songs for a large number of musically relevant words. We also show that our audition system is general by learning a model that can annotate and retrieve sound effects.Index Terms-Audio annotation and retrieval, music information retrieval, semantic music analysis.

No abstract

Query-by-semantic-description (QBSD) is a natural paradigm for retrieving content from large databases of music. A major impediment to the development of good QBSD systems for music information retrieval has been the lack of a cleanlylabeled, publicly-available, heterogeneous data set of songs and associated annotations. We have collected the Computer Audition Lab 500-song (CAL500) data set by having humans listen to and annotate songs using a survey designed to capture 'semantic associations' between music and words. We adapt the supervised multi-class labeling (SML) model, which has shown good performance on the task of image retrieval, and use the CAL500 data to learn a model for music retrieval. The model parameters are estimated using the weighted mixture hierarchies expectation-maximization algorithm which has been specifically designed to handle realvalued semantic association between words and songs, rather than binary class labels. The output of the SML model, a vector of class-conditional probabilities, can be interpreted as a semantic multinomial distribution over a vocabulary. By also representing a semantic query as a query multinomial distribution, we can quickly rank order the songs in a database based on the Kullback-Leibler divergence between the query multinomial and each song's semantic multinomial. Qualitative and quantitative results demonstrate that our SML model can both annotate a novel song with meaningful words and retrieve relevant songs given a multi-word, text-based query.

We present "Herd It", a competitive, online, multi-player game that has the implicit benefit of collecting tags for music. We describe Herd It's user-centered design process and demonstrate that the game can collect both musical and social data. This data can be used to build machine learning models that automatically associate music with tags. Herd It differs from previous "games with a purpose" in that it is designed to be social: the game runs on the Facebook online social network and scoring is based on consensus between a large group of listeners -"the Herd". By presenting music in a social context, Herd It adds demographic context to the semantic music descriptions that it collects. KeywordsAuditory I/O and sound in the UI, Distributed knowledge acquisition, Computer audition, Web-based games with a purpose