Related papers: Wavehax: Aliasing-Free Neural Waveform Synthesis B…

The performance of traditional linear spatial filters for speech enhancement is constrained by the physical size and number of channels of microphone arrays. For instance, for large microphone distances and high frequencies, spatial…

Spatial aliasing affects spaced microphone arrays, causing directional ambiguity above certain frequencies, degrading spatial and spectral accuracy of beamformers. Given the limitations of conventional signal processing and the scarcity of…

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…

Signal-dependent beamformers are advantageous over signal-independent beamformers when the acoustic scenario - be it real-world or simulated - is straightforward in terms of the number of sound sources, the ambient sound field and their…

Recent studies have shown that neural vocoders based on generative adversarial network (GAN) can generate audios with high quality. While GAN based neural vocoders have shown to be computationally much more efficient than those based on…

This paper proposes a novel bidirectional neural vocoder, named BiVocoder, capable both of feature extraction and reverse waveform generation within the short-time Fourier transform (STFT) domain. For feature extraction, the BiVocoder takes…

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…

Neural audio autoencoders create compact latent representations that preserve perceptually important information, serving as the foundation for both modern audio compression systems and generation approaches like next-token prediction and…

Whispered speech lacks vocal-fold excitation, making intelligible conversion challenging. We propose WhisperVC, a three-stage framework for low-resource whisper-to-normal (W2N) conversion that decouples cross-domain alignment from speech…

It is challenging to accelerate the training process while ensuring both high-quality generated voices and acceptable inference speed. In this paper, we propose a novel neural vocoder called InstructSing, which can converge much faster…

Multi-channel speech enhancement with ad-hoc sensors has been a challenging task. Speech model guided beamforming algorithms are able to recover natural sounding speech, but the speech models tend to be oversimplified or the inference would…

Context: Fourier transform (or lag) correlators in radio interferometers can serve as an efficient means of synthesising spectral channels. However aliasing corrupts the edge channels so they usually have to be excluded from the data set.…

Audio coding is an essential module in the real-time communication system. Neural audio codecs can compress audio samples with a low bitrate due to the strong modeling and generative capabilities of deep neural networks. To address the poor…

In the generator of typical Generative Adversarial Networks (GANs), a noise is inputted to generate fake samples via a series of convolutional operations. However, current noise generation models merely relies on the information from the…

The transformer architectures, based on self-attention mechanism and convolution-free design, recently found superior performance and booming applications in computer vision. However, the discontinuous patch-wise tokenization process…

We observe that despite their hierarchical convolutional nature, the synthesis process of typical generative adversarial networks depends on absolute pixel coordinates in an unhealthy manner. This manifests itself as, e.g., detail appearing…

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…

Denoising diffusion probabilistic models (DDPMs) and generative adversarial networks (GANs) are popular generative models for neural vocoders. The DDPMs and GANs can be characterized by the iterative denoising framework and adversarial…

Conventional vocoders are commonly used as analysis tools to provide interpretable features for downstream tasks such as speech synthesis and voice conversion. They are built under certain assumptions about the signals following signal…

The traditional vocoders have the advantages of high synthesis efficiency, strong interpretability, and speech editability, while the neural vocoders have the advantage of high synthesis quality. To combine the advantages of two vocoders,…