11 accepted papers
Lyric-to-melody generation is a highly challenging task in the field of AI music generation. Due to the difficulty of learning strict yet weak correlations between lyrics and melodies, previous methods have suffered from weak controllability, low-quality and poorly structured generation. To address…
The leak of anomalous information from input condition poses a great challenge to reconstruction-based anomaly detection. Recent diffusion-based methods respond to this issue by suppressing anomaly information for condition injection or in-sampling inversion. However, since they treat conditions as…
In-the-wild dynamic facial expression recognition (DFER) encounters a significant challenge in recognizing emotion-related expressions, which are often temporally and spatially diluted by emotion-irrelevant expressions and global context. Most prior DFER methods directly utilize coupled spatiotempor…
Multi-agent path finding (MAPF) involves finding collision-free paths for multiple agents while minimizing the total path costs. Explicit estimation conflict-based search (EECBS) represents a state-of-the-art variant of the widely used conflict-based search (CBS) method, offering bounded-suboptimal
Visual inspection by robotics and automation is widely applied in industry and daily life. Although dynamic coverage of mobile sensors has been developed for various tasks, existing methods are not suitable for visual inspection since sensing model is not taken into account. For this reason, this le
We study four data augmentation (DA) techniques and two model architectures on realistic data for sound event localization and detection (SELD). First, based on ResNet-Conformer (RC), we compare the four DA approaches on the realistic DCASE 2022 SELD test set which is often not easy to handle due to…
This study focuses on the design of a loss function for a deep neural network (DNN)-based model with two branches, which is used to solve sound event localization and detection (SELD) on low-resource realistic data. To this end, we employ a secondary network for audio classification, which provides…
To improve device robustness, a highly desirable key feature of a competitive data-driven acoustic scene classification (ASC) system, a novel two-stage system based on fully convolutional neural networks (CNNs) is proposed. Our two-stage system leverages on an ad-hoc score combination based on two C…
The multi-objective learning using minimum mean squared error criterion for DNN-based speech enhancement (MMSE-MOL-DNN) has been demonstrated to achieve better performance than single output DNN. However, one problem of MMSE-MOL-DNN is that the prediction error values on different targets have a ver…
In our previous work, a progressive learning framework for long short-term memory (LSTM)-based speech enhancement was proposed to improve the performance in low SNR environment, where each LSTM layer is guided to learn an intermediate target with a specific SNR gain via the MMSE criterion. However,…
Uncertainty principles in finite dimensional vector space have been studied extensively, however they cannot be applied to sparse representation of rational functions. This paper considers the sparse representation for a rational function under a pair of orthonormal rational function bases. We prove…