No abstract

Automatic knowledge extraction from music signals is a key component for most music organization and music information retrieval systems. In this paper, we consider the problem of instrument modelling and instrument classification from the rough audio data. Existing systems for automatic instrument classification operate normally on a relatively large number of features, from which those related to the spectrum of the audio signal are particularly relevant. In this paper, we confront two different models about the spectral characterization of musical instruments. The first assumes a constant envelope of the spectrum (i.e., independent from the pitch), whereas the second assumes a constant relation among the amplitude of the harmonics. The first model is related to the Mel Frequency Cepstrum Coefficients (MFCCs), while the second leads to what we will refer to as Harmonic Representation (HR). Experiments on a large database of real instrument recordings show that the first model offers a more satisfactory characterization, and therefore MFCCs should be preferred to HR for instrument modelling/classification.

A sound classification model is presented that can classify signals into music, noise and speech. The model extracts the pitch of the signal using the harmonic product spectrum. Based on the pitch estimate and a pitch error measure, features are created and used in a probabilistic model with softmax output function. Both linear and quadratic inputs are used. The model is trained on 2 hours of sound and tested on publically available data. A test classification error below 0.05 with 1 s classification windows is achieved. Further more it is shown that linear input performs as well as a quadratic, and that even though classification gets marginally better, not much is achieved by increasing the window size beyond 1 s.

We investigate concurrent 'Lifelog' audio recordings to locate segments from the same environment. We compare two techniques earlier proposed for pattern recognition in extended audio recordings, namely cross-correlation and a fingerprinting technique. If successful, such alignment can be used as a preprocessing step to select and synchronize recordings before further processing. The two methods perform similarly in classification, but fingerprinting scales better with the number of recordings, while cross-correlation can offer sample resolution synchronization. We propose and investigate the benefits of combining the two. In particular we show that the combination allows sample resolution synchronization and scalability.