相关论文: WaveGlow: A Flow-based Generative Network for Spee…

Generating realistic, dyadic talking head video requires ultra-low latency. Existing chunk-based methods require full non-causal context windows, introducing significant delays. This high latency critically prevents the immediate,…

Although many deep-learning-based super-resolution approaches have been proposed in recent years, because no ground truth is available in the inference stage, few can quantify the errors and uncertainties of the super-resolved results. For…

A key challenge in synthesizing audios from silent videos is the inherent trade-off between synthesis quality and inference efficiency in existing methods. For instance, flow matching based models rely on modeling instantaneous velocity,…

We introduce AV-Flow, an audio-visual generative model that animates photo-realistic 4D talking avatars given only text input. In contrast to prior work that assumes an existing speech signal, we synthesize speech and vision jointly. We…

Audio Super-Resolution is a set of techniques aimed at high-quality estimation of the given signal as if it would be sampled with higher sample rate. Among suggested methods there are diffusion and flow models (which are considered slower),…

Autoregressive convolutional neural networks (CNNs) have been widely exploited for sequence generation tasks such as audio synthesis, language modeling and neural machine translation. WaveNet is a deep autoregressive CNN composed of several…

Current auto-regressive (AR) LLMs, diffusion-based text/image generative models, and recent flow matching (FM) algorithms are capable of generating premium quality text/image samples. However, the inference or sample generation in these…

Building efficient and effective generative models for neural network weights has been a research focus of significant interest that faces challenges posed by the high-dimensional weight spaces of modern neural networks and their…

Various sources have reported the WaveNet deep learning architecture being able to generate high-quality speech, but to our knowledge there haven't been studies on the interpretation or visualization of trained WaveNets. This study…

Multistep inference is a bottleneck for real-time generative speech enhancement because flow- and diffusion-based systems learn an instantaneous velocity field and therefore rely on iterative ordinary differential equation (ODE) solvers. We…

Since the introduction of Generative Adversarial Networks (GANs) in speech synthesis, remarkable achievements have been attained. In a thorough exploration of vocoders, it has been discovered that audio waveforms can be generated at speeds…

Strong semantic representations improve the convergence and generation quality of diffusion and flow models. Existing approaches largely rely on external models, which require separate training, operate on misaligned objectives, and exhibit…

In this paper, we propose the FeatherWave, yet another variant of WaveRNN vocoder combining the multi-band signal processing and the linear predictive coding. The LPCNet, a recently proposed neural vocoder which utilized the linear…

Generative models have shown robust performance on speech enhancement and restoration tasks, but most prior approaches operate offline with high latency, making them unsuitable for streaming applications. In this work, we investigate the…

We propose a learning-based filter that allows us to directly modify a synthetic speech waveform into a natural speech waveform. Speech-processing systems using a vocoder framework such as statistical parametric speech synthesis and voice…

Despite the success of Large-Vision Language Models (LVLMs), general optimization objectives (e.g., standard MLE) fail to constrain visual trajectories, leading to language bias and hallucination. To mitigate this, current methods introduce…

Creating high-quality sound effects from videos and text prompts requires precise alignment between visual and audio domains, both semantically and temporally, along with step-by-step guidance for professional audio generation. However,…

Recent work has shown that Field-Programmable Gate Arrays (FPGAs) play an important role in the acceleration of Machine Learning applications. Initial specification of machine learning applications are often done using a high-level…

Target speaker extraction (TSE) aims to isolate a desired speaker's voice from a multi-speaker mixture using auxiliary information such as a reference utterance. Although recent advances in diffusion and flow-matching models have improved…

Diffusion models can learn rich representations during data generation, showing potential for Self-Supervised Learning (SSL), but they face a trade-off between generative quality and discriminative performance. Their iterative sampling also…