相关论文: Towards Practical Real-Time Low-Latency Music Sour…

The real-time processing of time series signals is a critical issue for many real-life applications. The idea of real-time processing is especially important in audio domain as the human perception of sound is sensitive to any kind of…

To enable the pre-trained models to be fine-tuned with local data on edge devices without sharing data with the cloud, we design an efficient split fine-tuning (SFT) framework for edge and cloud collaborative learning. We propose three…

Modern object detectors can rarely achieve short training time, fast inference speed, and high accuracy at the same time. To strike a balance among them, we propose the Training-Time-Friendly Network (TTFNet). In this work, we start with…

This paper introduces a novel Token-and-Duration Transducer (TDT) architecture for sequence-to-sequence tasks. TDT extends conventional RNN-Transducer architectures by jointly predicting both a token and its duration, i.e. the number of…

Latent spaces offer an efficient and effective means of summarizing data while implicitly preserving meta-information through relational encoding. We leverage these meta-embeddings to develop a modality-agnostic, unified encoder. Our method…

Time-frequency (TF) domain dual-path models achieve high-fidelity speech separation. While some previous state-of-the-art (SoTA) models rely on RNNs, this reliance means they lack the parallelizability, scalability, and versatility of…

End-to-end model, especially Recurrent Neural Network Transducer (RNN-T), has achieved great success in speech recognition. However, transducer requires a great memory footprint and computing time when processing a long decoding sequence.…

The efficient fusion of depth maps is a key part of most state-of-the-art 3D reconstruction methods. Besides requiring high accuracy, these depth fusion methods need to be scalable and real-time capable. To this end, we present a novel…

Time series forecasting is crucial in many fields, yet current deep learning models struggle with noise, data sparsity, and capturing complex multi-scale patterns. This paper presents MFF-FTNet, a novel framework addressing these challenges…

Speech separation on hearable devices can enable transformative augmented and enhanced hearing capabilities. However, state-of-the-art speech separation networks cannot run in real-time on tiny, low-power neural accelerators designed for…

Most of the current supervised automatic music transcription (AMT) models lack the ability to generalize. This means that they have trouble transcribing real-world music recordings from diverse musical genres that are not presented in the…

The main challenge for small object detection algorithms is to ensure accuracy while pursuing real-time performance. The RT-DETR model performs well in real-time object detection, but performs poorly in small object detection accuracy. In…

Airport performance prediction with a reasonable look-ahead time is a challenging task and has been attempted by various prior research. Traffic, demand, weather, and traffic management actions are all critical inputs to any prediction…

Existing RGB-D salient object detection (SOD) approaches concentrate on the cross-modal fusion between the RGB stream and the depth stream. They do not deeply explore the effect of the depth map itself. In this work, we design a single…

User mobility trajectory and mobile traffic data are essential for a wide spectrum of applications including urban planning, network optimization, and emergency management. However, large-scale and fine-grained mobility data remains…

Low-dose computed tomography (LDCT) reduces radiation exposure but suffers from image artifacts and loss of detail due to quantum and electronic noise, potentially impacting diagnostic accuracy. Transformer combined with diffusion models…

In this report we describe an ongoing line of research for solving single-channel source separation problems. Many monaural signal decomposition techniques proposed in the literature operate on a feature space consisting of a time-frequency…

Multimodal medical image fusion (MMIF) extracts the most meaningful information from multiple source images, enabling a more comprehensive and accurate diagnosis. Achieving high-quality fusion results requires a careful balance of…

The prosperity of deep learning contributes to the rapid progress in scene text detection. Among all the methods with convolutional networks, segmentation-based ones have drawn extensive attention due to their superiority in detecting text…

Extracting individual elements from music mixtures is a valuable tool for music production and practice. While neural networks optimized to mask or transform mixture spectrograms into the individual source(s) have been the leading approach,…