相关论文: Multi-Task Self-Supervised Pre-Training for Music …

There are two sub-tasks implied in the weakly-supervised SED: audio tagging and event boundary detection. Current methods which combine multi-task learning with SED requires annotations both for these two sub-tasks. Since there are only…

Music segmentation refers to the dual problem of identifying boundaries between, and labeling, distinct music segments, e.g., the chorus, verse, bridge etc. in popular music. The performance of a range of music segmentation algorithms has…

Recent breakthroughs in deep learning often rely on representation learning and knowledge transfer. In recent years, unsupervised and self-supervised techniques for learning speech representation were developed to foster automatic speech…

This thesis focuses on representation learning for sequence data over time or space, aiming to improve downstream sequence prediction tasks by using the learned representations. Supervised learning has been the most dominant approach for…

For high-resource languages like English, text classification is a well-studied task. The performance of modern NLP models easily achieves an accuracy of more than 90% in many standard datasets for text classification in English (Xie et…

Time-series representation learning can extract representations from data with temporal dynamics and sparse labels. When labeled data are sparse but unlabeled data are abundant, contrastive learning, i.e., a framework to learn a latent…

The performance of approaches to Music Instrument Classification, a popular task in Music Information Retrieval, is often impacted and limited by the lack of availability of annotated data for training. We propose to address this issue with…

Most existing approaches to disfluency detection heavily rely on human-annotated data, which is expensive to obtain in practice. To tackle the training data bottleneck, we investigate methods for combining multiple self-supervised…

Recent progress in singing voice separation has primarily focused on supervised deep learning methods. However, the scarcity of ground-truth data with clean musical sources has been a problem for long. Given a limited set of labeled data,…

Mood recognition is an important problem in music informatics and has key applications in music discovery and recommendation. These applications have become even more relevant with the rise of music streaming. Our work investigates the…

This paper addresses the problem of global tempo estimation in musical audio. Given that annotating tempo is time-consuming and requires certain musical expertise, few publicly available data sources exist to train machine learning models…

This work describes a self-supervised data augmentation approach used to improve learning models' performances when only a moderate amount of labeled data is available. Multiple copies of the original model are initially trained on the…

Vision transformers combined with self-supervised learning have enabled the development of models which scale across large datasets for several downstream tasks like classification, segmentation and detection. The low-shot learning…

This study explores using embedding rank as an unsupervised evaluation metric for general-purpose speech encoders trained via self-supervised learning (SSL). Traditionally, assessing the performance of these encoders is resource-intensive…

Music structure analysis (MSA) methods traditionally search for musically meaningful patterns in audio: homogeneity, repetition, novelty, and segment-length regularity. Hand-crafted audio features such as MFCCs or chromagrams are often used…

While supervised learning models have shown remarkable performance in various natural language processing (NLP) tasks, their success heavily relies on the availability of large-scale labeled datasets, which can be costly and time-consuming…

Speech emotion recognition (SER) systems find applications in various fields such as healthcare, education, and security and defense. A major drawback of these systems is their lack of generalization across different conditions. This…

Deep learning perception models require a massive amount of labeled training data to achieve good performance. While unlabeled data is easy to acquire, the cost of labeling is prohibitive and could create a tremendous burden on companies or…

Contrastive self-supervised learning has gained attention for its ability to create high-quality representations from large unlabelled data sets. A key reason that these powerful features enable data-efficient learning of downstream tasks…

The success of deep learning in computer vision is rooted in the ability of deep networks to scale up model complexity as demanded by challenging visual tasks. As complexity is increased, so is the need for large amounts of labeled data to…