This paper presents an application for performing melodic transformations to monophonic audio phrases. The system first extracts a melodic description from the audio. This description is presented to the user and can be stored and loaded in a MPEG-7 based format. A set of high-level transformations can then be applied to the melodic description. These high-level transformations are mapped into a set of low-level signal transformations and then applied to the audio signal. The algorithms for description extraction and audio transformation are also presented.

Download

In this paper we evaluate some of the alternative methods commonly applied in the first stages of the signal processing chain of automatic melody extraction systems. Namely, the first two stages are studied – the extraction of sinusoidal components and the computation of a time-pitch salience function, with the goal of determining the benefits and caveats of each approach under the specific context of predominant melody estimation. The approaches are evaluated on a data-set of polyphonic music containing several musical genres with different singing/playing styles, using metrics specifically designed for measuring the usefulness of each step for melody extraction. The results suggest that equal loudness filtering and frequency/amplitude correction methods provide significant improvements, whilst using a multi-resolution spectral transform results in only a marginal improvement compared to the standard STFT. The effect of key parameters in the computation of the salience function is also studied and discussed.

Download

Relative music loudness estimation is a MIR task that consists in dividing audio in segments of three classes: Foreground Music, Background Music and No Music. Given the temporal correlation of music, in this work we approach the task using a type of network with the ability to model temporal context: the Temporal Convolutional Network (TCN). We propose two architectures: a TCN, and a novel architecture resulting from the combination of a TCN with a Convolutional Neural Network (CNN) front-end. We name this new architecture CNN-TCN. We expect the CNN front-end to work as a feature extraction strategy to achieve a more efficient usage of the network’s parameters. We use the OpenBMAT dataset to train and test 40 TCN and 80 CNN-TCN models with two grid searches over a set of hyper-parameters. We compare our models with the two best algorithms submitted to the tasks of music detection and relative music loudness estimation in MIREX 2019. All our models outperform the MIREX algorithms even when using a lower number of parameters. The CNN-TCN emerges as the best architecture as all its models outperform all TCN models. We show that adding a CNN front-end to a TCN can actually reduce the number of parameters of the network while improving performance. The CNN front-end effectively works as a feature extractor producing consistent patterns that identify different combinations of music and non-music sounds and also helps in producing a smoother output in comparison to the TCN models.

Download