Related papers: DDSP: Differentiable Digital Signal Processing

An ideal music synthesizer should be both interactive and expressive, generating high-fidelity audio in realtime for arbitrary combinations of instruments and notes. Recent neural synthesizers have exhibited a tradeoff between…

Large, pretrained latent diffusion models (LDMs) have demonstrated an extraordinary ability to generate creative content, specialize to user data through few-shot fine-tuning, and condition their output on other modalities, such as semantic…

Denoising Diffusion Probabilistic Models (DDPMs) have achieved remarkable success in various image generation tasks compared with Generative Adversarial Nets (GANs). Recent work on semantic image synthesis mainly follows the de facto…

Timbre is a primary mode of expression in diverse musical contexts. However, prevalent audio-driven synthesis methods predominantly rely on pitch and loudness envelopes, effectively flattening timbral expression from the input. Our approach…

Conditional diffusion models have shown remarkable performance in various generative tasks, but training them requires large-scale datasets that often contain noise in conditional inputs, a.k.a. noisy labels. This noise leads to condition…

We present dPASP, a novel declarative probabilistic logic programming framework for differentiable neuro-symbolic reasoning. The framework allows for the specification of discrete probabilistic models with neural predicates, logic…

Denoising diffusion models (DDMs) have recently attracted increasing attention by showing impressive synthesis quality. DDMs are built on a diffusion process that pushes data to the noise distribution and the models learn to denoise. In…

Whisper generation is constrained by the difficulty of data collection. Because whispered speech has low acoustic amplitude, high-fidelity recording is challenging. In this paper, we introduce WhispSynth, a large-scale multilingual corpus…

While synthetic tabular data generation using Deep Generative Models (DGMs) offers a compelling solution to data scarcity and privacy concerns, their effectiveness relies on the availability of substantial training data, often lacking in…

Generative diffusion models, famous for their performance in image generation, are popular in various cross-domain applications. However, their use in the communication community has been mostly limited to auxiliary tasks like data modeling…

Font generation is a challenging problem especially for some writing systems that consist of a large number of characters and has attracted a lot of attention in recent years. However, existing methods for font generation are often in…

Score estimation is the backbone of score-based generative models (SGMs), especially denoising diffusion probabilistic models (DDPMs). A key result in this area shows that with accurate score estimates, SGMs can efficiently generate samples…

Learning from noisy labels is a challenge that arises in many real-world applications where training data can contain incorrect or corrupted labels. When fine-tuning language models with noisy labels, models can easily overfit the label…

While massive valuable deep models trained on large-scale data have been released to facilitate the artificial intelligence community, they may encounter attacks in deployment which leads to privacy leakage of training data. In this work,…

Denoising diffusion probabilistic models (DDPMs) have achieved high quality image generation without adversarial training, yet they require simulating a Markov chain for many steps to produce a sample. To accelerate sampling, we present…

Multiple moving sound source localization in real-world scenarios remains a challenging issue due to interaction between sources, time-varying trajectories, distorted spatial cues, etc. In this work, we propose to use deep learning…

Acoustic scene classification (ASC) suffers from device-induced domain shift, especially when labels are limited. Prior work focuses on curriculum-based training schedules that structure data presentation by ordering or reweighting training…

In this paper, AN is introduced into semantic communication systems for the first time to prevent semantic eavesdropping. However, the introduction of AN also poses challenges for the legitimate receiver in extracting semantic information.…

Many audio processing tasks require perceptual assessment. The ``gold standard`` of obtaining human judgments is time-consuming, expensive, and cannot be used as an optimization criterion. On the other hand, automated metrics are efficient…

Speech-to-speech translation is a typical sequence-to-sequence learning task that naturally has two directions. How to effectively leverage bidirectional supervision signals to produce high-fidelity audio for both directions? Existing…