相关论文: Alternating Approach-Putt Models for Multi-Stage S…

The expectation to deploy a universal neural network for speech enhancement, with the aim of improving noise robustness across diverse speech processing tasks, faces challenges due to the existing lack of awareness within static speech…

Diffusion models have recently shown promising results for difficult enhancement tasks such as the conditional and unconditional restoration of natural images and audio signals. In this work, we explore the possibility of leveraging a…

In this study we present a mixture of deep experts (MoDE) neural-network architecture for single microphone speech enhancement. Our architecture comprises a set of deep neural networks (DNNs), each of which is an 'expert' in a different…

When video is shot in noisy environment, the voice of a speaker seen in the video can be enhanced using the visible mouth movements, reducing background noise. While most existing methods use audio-only inputs, improved performance is…

In this paper, we present a causal speech signal improvement system that is designed to handle different types of distortions. The method is based on a generative diffusion model which has been shown to work well in scenarios with missing…

We propose ARiSE, an auto-regressive algorithm for multi-channel speech enhancement. ARiSE improves existing deep neural network (DNN) based frame-online multi-channel speech enhancement models by introducing auto-regressive connections,…

We propose UNIVERSE++, a universal speech enhancement method based on score-based diffusion and adversarial training. Specifically, we improve the existing UNIVERSE model that decouples clean speech feature extraction and diffusion. Our…

Enhancing speech quality is an indispensable yet difficult task as it is often complicated by a range of degradation factors. In addition to additive noise, reverberation, clipping, and speech attenuation can all adversely affect speech…

Since its inception, the field of deep speech enhancement has been dominated by predictive (discriminative) approaches, such as spectral mapping or masking. Recently, however, novel generative approaches have been applied to speech…

Audio captioning aims at generating natural language descriptions for audio clips automatically. Existing audio captioning models have shown promising improvement in recent years. However, these models are mostly trained via maximum…

While the use of deep neural networks has significantly boosted speaker recognition performance, it is still challenging to separate speakers in poor acoustic environments. Here speech enhancement methods have traditionally allowed improved…

Utilizing a human-perception-related objective function to train a speech enhancement model has become a popular topic recently. The main reason is that the conventional mean squared error (MSE) loss cannot represent auditory perception…

A typical neural speech enhancement (SE) approach mainly handles speech and noise mixtures, which is not optimal for singing voice enhancement scenarios. Music source separation (MSS) models treat vocals and various accompaniment components…

Diffusion models have shown promising results in speech enhancement, using a task-adapted diffusion process for the conditional generation of clean speech given a noisy mixture. However, at test time, the neural network used for score…

We investigate the problem of incorporating higher-level symbolic score-like information into Automatic Music Transcription (AMT) systems to improve their performance. We use recurrent neural networks (RNNs) and their variants as music…

PercepNet, a recent extension of the RNNoise, an efficient, high-quality and real-time full-band speech enhancement technique, has shown promising performance in various public deep noise suppression tasks. This paper proposes a new…

We propose PromptBERT, a novel contrastive learning method for learning better sentence representation. We firstly analyze the drawback of current sentence embedding from original BERT and find that it is mainly due to the static token…

This letter introduces a novel speech enhancement method in the Hilbert-Huang Transform domain to mitigate the effects of acoustic impulsive noises. The estimation and selection of noise components is based on the impulsiveness index of…

Speech enhancement (SE) based on diffusion probabilistic models has exhibited impressive performance, while requiring a relatively high number of function evaluations (NFE). Recently, SE based on flow matching has been proposed, which…

Neural sequence-to-sequence systems deliver state-of-the-art performance for automatic speech recognition. When using appropriate modeling units, e.g., byte-pair encoding, these systems are in principle open vocabulary systems. In practice,…