Related papers: Quasi-Periodic Parallel WaveGAN Vocoder: A Non-aut…

Automatic speech synthesis is a challenging task that is becoming increasingly important as edge devices begin to interact with users through speech. Typical text-to-speech pipelines include a vocoder, which translates intermediate audio…

We propose Universal MelGAN, a vocoder that synthesizes high-fidelity speech in multiple domains. To preserve sound quality when the MelGAN-based structure is trained with a dataset of hundreds of speakers, we added multi-resolution…

This paper presents a novel speech phase prediction model which predicts wrapped phase spectra directly from amplitude spectra by neural networks. The proposed model is a cascade of a residual convolutional network and a parallel estimation…

Conditional waveform synthesis models learn a distribution of audio waveforms given conditioning such as text, mel-spectrograms, or MIDI. These systems employ deep generative models that model the waveform via either sequential…

The zero-shot scenario for speech generation aims at synthesizing a novel unseen voice with only one utterance of the target speaker. Although the challenges of adapting new voices in zero-shot scenario exist in both stages -- acoustic…

Previous works (Donahue et al., 2018a; Engel et al., 2019a) have found that generating coherent raw audio waveforms with GANs is challenging. In this paper, we show that it is possible to train GANs reliably to generate high quality…

Generative adversarial network (GAN) based vocoders have achieved significant attention in speech synthesis with high quality and fast inference speed. However, there still exist many noticeable spectral artifacts, resulting in the quality…

Generative adversarial network (GAN) models can synthesize highquality audio signals while ensuring fast sample generation. However, they are difficult to train and are prone to several issues including mode collapse and divergence. In this…

In this paper, we suggest a new parallel, non-causal and shallow waveform domain architecture for speech enhancement based on FFTNet, a neural network for generating high quality audio waveform. In contrast to other waveform based…

Restoring speech communication from neural signals is a central goal of brain-computer interface research, yet EEG-based speech reconstruction remains challenging due to limited spatial resolution, susceptibility to noise, and the absence…

This paper introduces an improved generative model for statistical parametric speech synthesis (SPSS) based on WaveNet under a multi-task learning framework. Different from the original WaveNet model, the proposed Multi-task WaveNet employs…

Deep generative models have achieved significant progress in speech synthesis to date, while high-fidelity singing voice synthesis is still an open problem for its long continuous pronunciation, rich high-frequency parts, and strong…

Recently, GAN-based neural vocoders such as Parallel WaveGAN, MelGAN, HiFiGAN, and UnivNet have become popular due to their lightweight and parallel structure, resulting in a real-time synthesized waveform with high fidelity, even on a CPU.…

This paper focuses on using voice conversion (VC) to improve the speech intelligibility of surgical patients who have had parts of their articulators removed. Due to the difficulty of data collection, VC without parallel data is highly…

Superconducting quantum computer is manufactured based on semiconductor process which makes qubits integration possible. At the same time, this kind of qubit exhibits high performance fidelity, de-coherence time, scalability and requires a…

Neural vocoders model the raw audio waveform and synthesize high-quality audio, but even the highly efficient ones, like MB-MelGAN and LPCNet, fail to run real-time on a low-end device like a smartglass. A pure digital signal processing…

Deep learning has become a de facto method of choice for speech enhancement tasks with significant improvements in speech quality. However, real-time processing with reduced size and computations for low-power edge devices drastically…

Most neural vocoders are limited to one type: either GAN or diffusion-based. While state-of-the-art models like Vocos and WaveNeXt use powerful ConvNeXt-based generators, they have only been used in GAN frameworks and have limited…

Auditory stimulation of EEG slow waves (SW) during non-rapid eye movement (NREM) sleep has shown to improve cognitive function when it is delivered at the up-phase of SW. SW enhancement is particularly desirable in subjects with…

The development of neural vocoders (NVs) has resulted in the high-quality and fast generation of waveforms. However, conventional NVs target a single sampling rate and require re-training when applied to different sampling rates. A suitable…