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

In recent years, neural vocoders have surpassed classical speech generation approaches in naturalness and perceptual quality of the synthesized speech. Computationally heavy models like WaveNet and WaveGlow achieve best results, while…

Mean flow (MeanFlow) enables efficient, high-fidelity image generation, yet its single-function evaluation (1-NFE) generation often cannot yield compelling results. We address this issue by introducing RMFlow, an efficient multimodal…

Speech enhancement (SE) improves degraded speech's quality, with generative models like flow matching gaining attention for their outstanding perceptual quality. However, the flow-based model requires multiple numbers of function…

We present VoiceRestore, a novel approach to restoring the quality of speech recordings using flow-matching Transformers trained in a self-supervised manner on synthetic data. Our method tackles a wide range of degradations frequently found…

Recently, universal waveform generation tasks have been investigated conditioned on various out-of-distribution scenarios. Although GAN-based methods have shown their strength in fast waveform generation, they are vulnerable to…

This paper proposes a novel way of doing audio synthesis at the waveform level using Transformer architectures. We propose a deep neural network for generating waveforms, similar to wavenet. This is fully probabilistic, auto-regressive, and…

Flow-based generative models, conceptually attractive due to tractability of both the exact log-likelihood computation and latent-variable inference, and efficiency of both training and sampling, has led to a number of impressive empirical…

Recent advances in speech synthesis suggest that limitations such as the lossy nature of the amplitude spectrum with minimum phase approximation and the over-smoothing effect in acoustic modeling can be overcome by using advanced machine…

State-of-the-art deep learning systems such as TensorFlow and PyTorch tightly couple the model with the underlying hardware. This coupling requires the user to modify application logic in order to run the same job across a different set of…

Traditional speech enhancement systems produce speech with compromised quality. Here we propose to use the high quality speech generation capability of neural vocoders for better quality speech enhancement. We term this parametric…

Generative models are capable to address difficult problems with non-unique solutions like bandwidth extension and gap filling, removing highly non-linear artifacts from codecs, clipping and distortion, as opposed to removing linear…

Traditional structured prediction models try to learn the conditional likelihood, i.e., p(y|x), to capture the relationship between the structured output y and the input features x. For many models, computing the likelihood is intractable.…

Diffusion models have recently been shown to be relevant for high-quality speech generation. Most work has been focused on generating spectrograms, and as such, they further require a subsequent model to convert the spectrogram to a…

In this paper, we present a vocoder-free framework for audio super-resolution that employs a flow matching generative model to capture the conditional distribution of complex-valued spectral coefficients. Unlike conventional two-stage…

Diffusion-based generative models have greatly impacted the speech processing field in recent years, exhibiting high speech naturalness and spawning a new research direction. Their application in real-time communication is, however, still…

Flow-based generative models show great potential in image synthesis due to its reversible pipeline and exact log-likelihood target, yet it suffers from weak ability for conditional image synthesis, especially for multi-label or unaware…

In this work, we consider the radio resource allocation problem in a wireless system with various integrated functionalities, such as communication, sensing and computing. We design suitable resource management techniques that can…

This Ph.D. thesis focuses on developing a system for high-quality speech synthesis and voice conversion. Vocoder-based speech analysis, manipulation, and synthesis plays a crucial role in various kinds of statistical parametric speech…

This paper proposes a novel neural denoising vocoder that can generate clean speech waveforms from noisy mel-spectrograms. The proposed neural denoising vocoder consists of two components, i.e., a spectrum predictor and a enhancement…

Recent advances in visually-induced audio generation are based on sampling short, low-fidelity, and one-class sounds. Moreover, sampling 1 second of audio from the state-of-the-art model takes minutes on a high-end GPU. In this work, we…