相关论文: Designing Neural Synthesizers for Low-Latency Inte…

Recently, a variational autoencoder (VAE)-based single-channel speech enhancement system using Bayesian permutation training has been proposed, which uses two pretrained VAEs to obtain latent representations for speech and noise. Based on…

Test-Time Adaptation (TTA) adjusts models using unlabeled test data to handle dynamic distribution shifts. However, existing methods rely on frequent adaptation and high computational cost, making them unsuitable for resource-constrained…

This paper introduces Stress-Aware Learning, a resilient neural training paradigm in which deep neural networks dynamically adjust their optimization behavior - whether under stable training regimes or in settings with uncertain dynamics -…

Generative models serve as powerful tools for modeling the real world, with mainstream diffusion models, particularly those based on the latent diffusion model paradigm, achieving remarkable progress across various tasks, such as image and…

Existing deep learning based speech enhancement mainly employ a data-driven approach, which leverage large amounts of data with a variety of noise types to achieve noise removal from noisy signal. However, the high dependence on the data…

Non-invasive brain-computer interfaces (BCIs) have the potential to enable intuitive control of prosthetic limbs for individuals with upper limb amputations. However, existing EEG-based control systems face challenges related to signal…

We present Interactive Neural Video Editing (INVE), a real-time video editing solution, which can assist the video editing process by consistently propagating sparse frame edits to the entire video clip. Our method is inspired by the recent…

Quantization has become a predominant approach for model compression, enabling deployment of large models trained on GPUs onto smaller form-factor devices for inference. Quantization-aware training (QAT) optimizes model parameters with…

This paper presents a circuit-algorithm co-design framework for learnable analog front-end (AFE) in audio signal classification. Designing AFE and backend classifiers separately is a common practice but non-ideal, as shown in this paper.…

Recently, audio-visual speech enhancement has been tackled in the unsupervised settings based on variational auto-encoders (VAEs), where during training only clean data is used to train a generative model for speech, which at test time is…

In recent years, research on music transcription has focused mainly on architecture design and instrument-specific data acquisition. With the lack of availability of diverse datasets, progress is often limited to solo-instrument tasks such…

Accurate fault detection in high-dimensional industrial environments remains a major challenge due to the inherent complexity, noise, and redundancy in sensor data. This paper introduces CLAIRE, i.e., a hybrid end-to-end learning framework…

Connecting large libraries of digitized audio recordings to their corresponding sheet music images has long been a motivation for researchers to develop new cross-modal retrieval systems. In recent years, retrieval systems based on…

We investigate large-scale latent variable models (LVMs) for neural story generation -- an under-explored application for open-domain long text -- with objectives in two threads: generation effectiveness and controllability. LVMs,…

The popularity of applying machine learning techniques in musical domains has created an inherent availability of freely accessible pre-trained neural network (NN) models ready for use in creative applications. This work outlines the…

Hollow-core fibers offer superior loss and latency characteristics compared to solid-core alternatives, yet the geometric complexity of nested antiresonance nodeless fibers (NANFs) makes traditional optimization computationally prohibitive.…

Class Activation Maps (CAMs) are one of the important methods for visualizing regions used by deep learning models. Yet their robustness to different noise remains underexplored. In this work, we evaluate and report the resilience of…

Text-to-audio diffusion models produce high-fidelity audio but require tens of function evaluations (NFEs), incurring multi-second latency and limited throughput. We present SoundWeaver, the first training-free, model-agnostic serving…

Wavetable synthesis generates quasi-periodic waveforms of musical tones by interpolating a list of waveforms called wavetable. As generative models that utilize latent representations offer various methods in waveform generation for musical…

In this paper, we propose a noise-aware encoder-decoder framework to disentangle a clean saliency predictor from noisy training examples, where the noisy labels are generated by unsupervised handcrafted feature-based methods. The proposed…