Related papers: Speaker-independent raw waveform model for glottal…

In this work, we propose a new mathematical vocoder algorithm(modified spectral inversion) that generates a waveform from acoustic features without phase estimation. The main benefit of using our proposed method is that it excludes the…

Neural vocoders have recently advanced waveform generation, yielding natural and expressive audio. Among these approaches, iSTFT-based vocoders have recently gained attention. They predict a complex-valued spectrogram and then synthesize…

This paper presents a refinement framework of WaveNet vocoders for variational autoencoder (VAE) based voice conversion (VC), which reduces the quality distortion caused by the mismatch between the training data and testing data.…

In this paper, we propose a novel conditional convolution network, named location-variable convolution, to model the dependencies of the waveform sequence. Different from the use of unified convolution kernels in WaveNet to capture the…

The presence of multiple talkers in the surrounding environment poses a difficult challenge for real-time speech communication systems considering the constraints on network size and complexity. In this paper, we present Personalized…

Formant synthesis aims to generate speech with controllable formant structures, enabling precise control of vocal resonance and phonetic features. However, while existing formant synthesis approaches enable precise formant manipulation,…

Most neural network speech enhancement models ignore speech production mathematical models by directly mapping Fourier transform spectrums or waveforms. In this work, we propose a neural source filter network for speech enhancement.…

Here we present a novel approach to conditioning the SampleRNN generative model for voice conversion (VC). Conventional methods for VC modify the perceived speaker identity by converting between source and target acoustic features. Our…

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…

Separating target speech from mixed signals containing flexible speaker quantities presents a challenging task. While existing methods demonstrate strong separation performance and noise robustness, they predominantly assume prior knowledge…

For articulatory-to-acoustic mapping using deep neural networks, typically spectral and excitation parameters of vocoders have been used as the training targets. However, vocoding often results in buzzy and muffled final speech quality.…

This paper presents a reverberation module for source-filter-based neural vocoders that improves the performance of reverberant effect modeling. This module uses the output waveform of neural vocoders as an input and produces a reverberant…

Neural source-filter (NSF) models are deep neural networks that produce waveforms given input acoustic features. They use dilated-convolution-based neural filter modules to filter sine-based excitation for waveform generation, which is…

Custom voice is to construct a personal speech synthesis system by adapting the source speech synthesis model to the target model through the target few recordings. The solution to constructing a custom voice is to combine an adaptive…

Target speech extraction remains difficult for compact devices because monaural neural models lack spatial evidence and classical beamformers lose resolving power when the microphone aperture is only a few centimetres. We present IsoNet, a…

Noise suppression systems generally produce output speech with compromised quality. We propose to utilize the high quality speech generation capability of neural vocoders for noise suppression. We use a neural network to predict clean…

Recently, deep learning-based generative models have been introduced to generate singing voices. One approach is to predict the parametric vocoder features consisting of explicit speech parameters. This approach has the advantage that the…

Generative deep neural networks are widely used for speech synthesis, but most existing models directly generate waveforms or spectral outputs. Humans, however, produce speech by controlling articulators, which results in the production of…

This paper introduces WaveGrad, a conditional model for waveform generation which estimates gradients of the data density. The model is built on prior work on score matching and diffusion probabilistic models. It starts from a Gaussian…

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…