相关论文: Wave-Trainer-Fit: Neural Vocoder with Trainable Pr…

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,…

Singing voice synthesis (SVS) has seen remarkable advancements in recent years. However, compared to speech and general audio data, publicly available singing datasets remain limited. In practice, this data scarcity often leads to…

Although convolutional neural networks (CNNs) have achieved remarkable progress in weakly supervised semantic segmentation (WSSS), the effective receptive field of CNN is insufficient to capture global context information, leading to…

Automatic speech recognition (ASR) has gained remarkable successes thanks to recent advances of deep learning, but it usually degrades significantly under real-world noisy conditions. Recent works introduce speech enhancement (SE) as…

Recently, GAN based speech synthesis methods, such as MelGAN, have become very popular. Compared to conventional autoregressive based methods, parallel structures based generators make waveform generation process fast and stable. However,…

Speech separation (SS) seeks to disentangle a multi-talker speech mixture into single-talker speech streams. Although SS can be generally achieved using offline methods, such a processing paradigm is not suitable for real-time streaming…

This paper proposes voicing-aware conditional discriminators for Parallel WaveGAN-based waveform synthesis systems. In this framework, we adopt a projection-based conditioning method that can significantly improve the discriminator's…

Self-Supervised Learning (SSL) has become a powerful solution to extract rich representations from unlabeled data. Yet, SSL research is mostly focused on clean, curated and high-quality datasets. As a result, applying SSL on noisy data…

The approximation and convergence properties of implicit neural representations (INRs) are known to be highly sensitive to parameter initialization strategies. While several data-driven initialization methods demonstrate significant…

Various threats posed by the progress in text-to-speech (TTS) have prompted the need to reliably trace synthesized speech. However, contemporary approaches to this task involve adding watermarks to the audio separately after generation, a…

In voice conversion (VC), it is crucial to preserve complete semantic information while accurately modeling the target speaker's timbre and prosody. This paper proposes FabasedVC to achieve VC with enhanced similarity in timbre, prosody,…

Understanding and controlling latent representations in deep generative models is a challenging yet important problem for analyzing, transforming and generating various types of data. In speech processing, inspiring from the anatomical…

We present SoundStream, a novel neural audio codec that can efficiently compress speech, music and general audio at bitrates normally targeted by speech-tailored codecs. SoundStream relies on a model architecture composed by a fully…

Training deep networks with noisy labels leads to poor generalization and degraded accuracy due to overfitting to label noise. Existing approaches for learning with noisy labels often rely on the availability of a clean subset of data. By…

The lack of clean speech is a practical challenge to the development of speech enhancement systems, which means that there is an inevitable mismatch between their training criterion and evaluation metric. In response to this unfavorable…

Denoising diffusion probabilistic models have been recently proposed to generate high-quality samples by estimating the gradient of the data density. The framework defines the prior noise as a standard Gaussian distribution, whereas the…

Over the recent years, various deep learning-based methods were proposed for extracting a fixed-dimensional embedding vector from speech signals. Although the deep learning-based embedding extraction methods have shown good performance in…

Modern audio generation predominantly relies on latent-space compression, introducing additional complexity and potential information loss. In this work, we challenge this paradigm with WavFlow, a framework that generates high-fidelity…

Accurate prediction of material properties facilitates the discovery of novel materials with tailored functionalities. Deep learning models have recently shown superior accuracy and flexibility in capturing structure-property relationships.…

Recently, speech enhancement (SE) based on deep speech prior has attracted much attention, such as the variational auto-encoder with non-negative matrix factorization (VAE-NMF) architecture. Compared to conventional approaches that…