Related papers: Analysing Diffusion-based Generative Approaches ve…
Diffusion-based generative models have exhibited powerful generative performance in recent years. However, as many attributes exist in the data distribution and owing to several limitations of sharing the model parameters across all levels…
Many approaches have been proposed to use diffusion models to augment training datasets for downstream tasks, such as classification. However, diffusion models are themselves trained on large datasets, often with noisy annotations, and it…
The use of discriminators to train or fine-tune generative models has proven to be a rather successful framework. A notable example is Generative Adversarial Networks (GANs) that minimize a loss incurred by training discriminators along…
Diffusion models, a powerful and universal generative AI technology, have achieved tremendous success in computer vision, audio, reinforcement learning, and computational biology. In these applications, diffusion models provide flexible…
The advancements in generative modeling, particularly the advent of diffusion models, have sparked a fundamental question: how can these models be effectively used for discriminative tasks? In this work, we find that generative models can…
Recent progress in Quality Diversity Reinforcement Learning (QD-RL) has enabled learning a collection of behaviorally diverse, high performing policies. However, these methods typically involve storing thousands of policies, which results…
Non-autoregressive (NAR) text generation has attracted much attention in the field of natural language processing, which greatly reduces the inference latency but has to sacrifice the generation accuracy. Recently, diffusion models, a class…
Recently, neural speech codecs (NSCs) trained as generative models have shown superior performance compared to conventional codecs at low bitrates. Although most state-of-the-art NSCs are trained as Generative Adversarial Networks (GANs),…
Dysarthric speech poses significant challenges for automatic speech recognition (ASR) systems due to its high variability and reduced intelligibility. In this work we explore the use of diffusion models for dysarthric speech enhancement,…
Learning from a large corpus of data, pre-trained models have achieved impressive progress nowadays. As popular generative pre-training, diffusion models capture both low-level visual knowledge and high-level semantic relations. In this…
Dysarthric speech reconstruction (DSR) aims to convert dysarthric speech into comprehensible speech while maintaining the speaker's identity. Despite significant advancements, existing methods often struggle with low speech intelligibility…
Animating virtual avatars to make co-speech gestures facilitates various applications in human-machine interaction. The existing methods mainly rely on generative adversarial networks (GANs), which typically suffer from notorious mode…
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,…
This paper is about developing personalized speech synthesis systems with recordings of mildly impaired speech. In particular, we consider consonant and vowel alterations resulted from partial glossectomy, the surgical removal of part of…
Semantic communications mark a paradigm shift from bit-accurate transmission toward meaning-centric communication, essential as wireless systems approach theoretical capacity limits. The emergence of generative AI has catalyzed generative…
Generative models have excelled in audio tasks using approaches such as language models, diffusion, and flow matching. However, existing generative approaches for speech enhancement (SE) face notable challenges: language model-based methods…
Prompt learning has demonstrated promising results in fine-tuning pre-trained multimodal models. However, the performance improvement is limited when applied to more complex and fine-grained tasks. The reason is that most existing methods…
In this paper we present a method for single-channel wind noise reduction using our previously proposed diffusion-based stochastic regeneration model combining predictive and generative modelling. We introduce a non-additive speech in noise…
Diffusion-based generative models (DBGMs) perturb data to a target noise distribution and reverse this process to generate samples. The choice of noising process, or inference diffusion process, affects both likelihoods and sample quality.…
Restoring degraded music signals is essential to enhance audio quality for downstream music manipulation. Recent diffusion-based music restoration methods have demonstrated impressive performance, and among them, diffusion posterior…