In this work, we investigate an approach that relies on contrastive learning and music metadata as a weak source of supervision to train music representation models. Recent studies show that contrastive learning can be used with editorial metadata (e.g., artist or album name) to learn audio representations that are useful for different classification tasks. In this paper, we extend this idea to using playlist data as a source of music similarity information and investigate three approaches to generate anchor and positive track pairs. We evaluate these approaches by fine-tuning the pre-trained models for music multi-label classification tasks (genre, mood, and instrument tagging) and music similarity. We find that creating anchor and positive track pairs by relying on co-occurrences in playlists provides better music similarity and competitive classification results compared to choosing tracks from the same artist as in previous works. Additionally, our best pre-training approach based on playlists provides superior classification performance for most datasets.

Most existing datasets for sound event recognition (SER) are relatively small and/or domain-specific, with the exception of AudioSet, based on over 2 M tracks from YouTube videos and encompassing over 500 sound classes. However, AudioSet is not an open dataset as its official release consists of pre-computed audio features. Downloading the original audio tracks can be problematic due to YouTube videos gradually disappearing and usage rights issues. To provide an alternative benchmark dataset and thus foster SER research, we introduceFSD50K, an open dataset containing over 51 k audio clips totalling over 100 h of audio manually labeled using 200 classes drawn from the AudioSet Ontology. The audio clips are licensed under Creative Commons licenses, making the dataset freely distributable (including waveforms). We provide a detailed description of the FSD50K creation process, tailored to the particularities of Freesound data, including challenges encountered and solutions adopted. We include a comprehensive dataset characterization along with discussion of limitations and key factors to allow its audio-informed usage. Finally, we conduct sound event classification experiments to provide baseline systems as well as insight on the main factors to consider when splitting Freesound audio data for SER. Our goal is to develop a dataset to be widely adopted by the community as a new open benchmark for SER research.

Self-supervised audio representation learning offers an attractive alternative for obtaining generic audio embeddings, capable to be employed into various downstream tasks. Published approaches that consider both audio and words/tags associated with audio do not employ text processing models that are capable to generalize to tags unknown during training. In this work we propose a method for learning audio representations using an audio autoencoder (AAE), a general word embed-dings model (WEM), and a multi-head self-attention (MHA) mechanism. MHA attends on the output of the WEM, pro-viding a contextualized representation of the tags associated with the audio, and we align the output of MHA with the out-put of the encoder of AAE using a contrastive loss. We jointly optimize AAE and MHA and we evaluate the audio representations (i.e. the output of the encoder of AAE) by utilizing them in three different downstream tasks, namely sound, music genre, and music instrument classification. Our results show that employing multi-head self-attention with multiple heads in the tag-based network can induce better learned audio representations.

Modeling various aspects that make a music piece unique is a challenging task, requiring the combination of multiple sources of information. Deep learning is commonly used to obtain representations using various sources of information, such as the audio, interactions between users and songs, or associated genre metadata. Recently, contrastive learning has led to representations that generalize better compared to traditional supervised methods. In this paper, we present a novel approach that combines multiple types of information related to music using cross-modal contrastive learning, allowing us to learn an audio feature from heterogeneous data simultaneously. We align the latent representations obtained from playlists-track interactions, genre metadata, and the tracks' audio, by maximizing the agreement between these modality representations using a contrastive loss. We evaluate our approach in three tasks, namely, genre classification, playlist continuation and automatic tagging. We compare the performances with a baseline audio-based CNN trained to predict these modalities. We also study the importance of including multiple sources of information when training our embedding model. The results suggest that the proposed method outperforms the baseline in all the three downstream tasks and achieves comparable performance to the state-of-the-art.

We present a deep neural network-based methodology for synthesising percussive sounds with control over high-level timbral characteristics of the sounds. This approach allows for intuitive control of a synthesizer, enabling the user to shape sounds without extensive knowledge of signal processing. We use a feedforward convolutional neural network-based architecture, which is able to map input parameters to the corresponding waveform. We propose two datasets to evaluate our approach on both a restrictive context, and in one covering a broader spectrum of sounds. The timbral features used as parameters are taken from recent literature in signal processing. We also use these features for evaluation and validation of the presented model, to ensure that changing the input parameters produces a congruent waveform with the desired characteristics. Finally, we evaluate the quality of the output sound using a subjective listening test. We provide sound examples and the system's source code for reproducibility.

The large size of nowadays' online multimedia databases makes retrieving their content a difficult and time-consuming task. Users of online sound collections typically submit search queries that express a broad intent, often making the system return large and unmanageable result sets. Search Result Clustering is a technique that organises search-result content into coherent groups, which allows users to identify useful subsets in their results. Obtaining coherent and distinctive clusters that can be explored with a suitable interface is crucial for making this technique a useful complement of traditional search engines. In our work, we propose a graph-based approach using audio features for clustering diverse sound collections obtained when querying large online databases. We propose an approach to assess the performance of different features at scale, by taking advantage of the metadata associated with each sound. This analysis is complemented with an evaluation using ground-truth labels from manually annotated datasets. We show that using a confidence measure for discarding inconsistent clusters improves the quality of the partitions. After identifying the most appropriate features for clustering, we conduct an experiment with users performing a sound design task, in order to evaluate our approach and its user interface. A qualitative analysis is carried out including usability questionnaires and semi-structured interviews. This provides us with valuable new insights regarding the features that promote efficient interaction with the clusters.

As sound event classification moves towards larger datasets, issues of label noise become inevitable. Web sites can supply large volumes of user-contributed audio and metadata, but inferring labels from this metadata introduces errors due to unreliable inputs, and limitations in the mapping. There is, however, little research into the impact of these errors. To foster the investigation of label noise in sound event classification we present FSDnoisy18k, a dataset containing 42.5 hours of audio across 20 sound classes, including a small amount of manually-labeled data and a larger quantity of real-world noisy data. We characterize the label noise empirically, and provide a CNN baseline system. Experiments suggest that training with large amounts of noisy data can outperform training with smaller amounts of carefully-labeled data. We also show that noise-robust loss functions can be effective in improving performance in presence of corrupted labels.

The intuitive control of voice transformation (e.g., age/sex, emotions) is useful to extend the expressive repertoire of a voice. This paper explores the role of glottal source parameters for the control of voice transformation. First, the SVLN speech synthesizer (Separation of the Vocal-tract with the Liljencrants-fant model plus Noise) is used to represent the glottal source parameters (and thus, voice quality) during speech analysis and synthesis. Then, a simple statistical method is presented to control speech parameters during voice transformation: a GMM is used to model the speech parameters of a voice, and regressions are then used to adapt the GMMs statistics (mean and variance) to a control parameter (e.g., age/sex, emotions). A subjective experiment conducted on the control of perceptual age proves the importance of the glottal source parameters for the control of voice transformation, and shows the efficiency of the statistical model to control voice parameters while preserving a high-quality of the voice transformation.