Related papers: A Neural Denoising Vocoder for Clean Waveform Gene…

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…

This paper presents a method of decoupled pronunciation and prosody modeling to improve the performance of meta-learning-based multilingual speech synthesis. The baseline meta-learning synthesis method adopts a single text encoder with a…

This paper introduces R-MelNet, a two-part autoregressive architecture with a frontend based on the first tier of MelNet and a backend WaveRNN-style audio decoder for neural text-to-speech synthesis. Taking as input a mixed sequence of…

Deploying speech enhancement (SE) systems in wearable devices, such as smart glasses, is challenging due to the limited computational resources on the device. Although deep learning methods have achieved high-quality results, their…

We propose an algorithm to denoise speakers from a single microphone in the presence of non-stationary and dynamic noise. Our approach is inspired by the recent success of neural network models separating speakers from other speakers and…

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…

This paper presents a neural vocoder based on a denoising diffusion probabilistic model (DDPM) incorporating explicit periodic signals as auxiliary conditioning signals. Recently, DDPM-based neural vocoders have gained prominence as…

Denoising is the process of removing noise from sound signals while improving the quality and adequacy of the sound signals. Denoising sound has many applications in speech processing, sound events classification, and machine failure…

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 propose a transformer-based architecture, called two-stage transformer neural network (TSTNN) for end-to-end speech denoising in the time domain. The proposed model is composed of an encoder, a two-stage transformer module…

We propose SpeakerNet - a new neural architecture for speaker recognition and speaker verification tasks. It is composed of residual blocks with 1D depth-wise separable convolutions, batch-normalization, and ReLU layers. This architecture…

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…

Ultra-low-bitrate speech coding is pivotal for bandwidth-constrained communication and deep compression, yet maintaining naturalness and speaker identity at such extreme bit budgets remains challenging due to pronounced information loss and…

We present a novel high-fidelity real-time neural vocoder called VocGAN. A recently developed GAN-based vocoder, MelGAN, produces speech waveforms in real-time. However, it often produces a waveform that is insufficient in quality or…

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…

Speech enhancement is a task to improve the intelligibility and perceptual quality of degraded speech signal. Recently, neural networks based methods have been applied to speech enhancement. However, many neural network based methods…

High quality speech capture has been widely studied for both voice communication and human computer interface reasons. To improve the capture performance, we can often find multi-microphone speech enhancement techniques deployed on various…

Most deep learning-based multi-channel speech enhancement methods focus on designing a set of beamforming coefficients to directly filter the low signal-to-noise ratio signals received by microphones, which hinders the performance of these…

In this study, we propose a dense frequency-time attentive network (DeFT-AN) for multichannel speech enhancement. DeFT-AN is a mask estimation network that predicts a complex spectral masking pattern for suppressing the noise and…

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…