Related papers: Synthia's Melody: A Benchmark Framework for Unsupe…
Stereo Depth Estimation in real-world environments poses significant challenges due to dynamic domain shifts, sparse or unreliable supervision, and the high cost of acquiring dense ground-truth labels. While recent Test-Time Adaptation…
This paper presents Sinsy, a deep neural network (DNN)-based singing voice synthesis (SVS) system. In recent years, DNNs have been utilized in statistical parametric SVS systems, and DNN-based SVS systems have demonstrated better…
Driven by the escalating global burden of mental health conditions, music-based interventions have attracted significant attention as a non-invasive, cost-effective modality for emotion regulation and psychological stress relief. However,…
Generating sound effects with controllable variations is a challenging task, traditionally addressed using sophisticated physical models that require in-depth knowledge of signal processing parameters and algorithms. In the era of…
Unsupervised Domain Adaptation (UDA) aims at improving the generalization capability of a model trained on a source domain to perform well on a target domain for which no labeled data is available. In this paper, we consider the semantic…
In this paper, we propose to pre-train audio encoders using synthetic patterns instead of real audio data. Our proposed framework consists of two key elements. The first one is Masked Autoencoder (MAE), a self-supervised learning framework…
Applications of deep learning to automatic multitrack mixing are largely unexplored. This is partly due to the limited available data, coupled with the fact that such data is relatively unstructured and variable. To address these…
This study focuses on the perception of music performances when contextual factors, such as room acoustics and instrument, change. We propose to distinguish the concept of "performance" from the one of "interpretation", which expresses the…
The generation of lyrics tightly connected to accompanying melodies involves establishing a mapping between musical notes and syllables of lyrics. This process requires a deep understanding of music constraints and semantic patterns at…
In speaker-independent speech emotion recognition, the training and testing samples are collected from diverse speakers, leading to a multi-domain shift challenge across the feature distributions of data from different speakers.…
To overcome the domain gap between synthetic and real-world datasets, unsupervised domain adaptation methods have been proposed for semantic segmentation. Majority of the previous approaches have attempted to reduce the gap either at the…
In recent years, image manipulation is becoming increasingly more accessible, yielding more natural-looking images, owing to the modern tools in image processing and computer vision techniques. The task of the identification of forged…
Label scarcity remains a major challenge in deep learning-based medical image segmentation. Recent studies use strong-weak pseudo supervision to leverage unlabeled data. However, performance is often hindered by inconsistencies between…
Automatic music transcription converts audio recordings into symbolic representations, facilitating music analysis, retrieval, and generation. A musical note is characterized by pitch, onset, and offset in an audio domain, whereas it is…
We study source-free unsupervised domain adaptation (SFUDA) for semantic segmentation, which aims to adapt a source-trained model to the target domain without accessing the source data. Many works have been proposed to address this…
Transformer architectures have transformed AI applications but remain complex to customize for domain experts lacking low-level implementation expertise. We introduce AttentionSmithy, a modular software package that simplifies transformer…
The issue of source-free time-series domain adaptations still gains scarce research attentions. On the other hand, existing approaches rely solely on time-domain features ignoring frequency components providing complementary information.…
We propose a fast probabilistic framework for identifying differential equations governing the dynamics of observed data. We recast the SINDy method within a Bayesian framework and use Gaussian approximations for the prior and likelihood to…
As large language models (LLMs) advance, their ability to perform in-context learning and few-shot language generation has improved significantly. This has spurred using LLMs to produce high-quality synthetic data to enhance the performance…
A novel approach for unsupervised domain adaptation for neural networks is proposed. It relies on metric-based regularization of the learning process. The metric-based regularization aims at domain-invariant latent feature representations…