相关论文: Wave-U-Net: A Multi-Scale Neural Network for End-t…

In this paper, we propose to extend the deep, complex U-Network architecture for speech enhancement by incorporating a probabilistic (i.e., variational) latent space model. The proposed model is evaluated against several ablated versions of…

This paper introduces a new method for multi-channel time domain speech separation in reverberant environments. A fully-convolutional neural network structure has been used to directly separate speech from multiple microphone recordings,…

Speech separation refers to extracting each individual speech source in a given mixed signal. Recent advancements in speech separation and ongoing research in this area, have made these approaches as promising techniques for pre-processing…

The source separation-based speech enhancement problem with multiple beamforming in reverberant indoor environments is addressed in this paper. We propose that more generic solutions should cope with time-varying dynamic scenarios with…

Audio source separation is a difficult machine learning problem and performance is measured by comparing extracted signals with the component source signals. However, if separation is motivated by the ultimate goal of re-mixing then…

Music, speech, and acoustic scene sound are often handled separately in the audio domain because of their different signal characteristics. However, as the image domain grows rapidly by versatile image classification models, it is necessary…

We introduce a U-net model for 360{\deg} acoustic source localization formulated as a spherical semantic segmentation task. Rather than regressing discrete direction-of-arrival (DoA) angles, our model segments beamformed audio maps (azimuth…

In this paper we propose a novel model for unconditional audio generation based on generating one audio sample at a time. We show that our model, which profits from combining memory-less modules, namely autoregressive multilayer…

Audio source separation is often achieved by estimating the magnitude spectrogram of each source, and then applying a phase recovery (or spectrogram inversion) algorithm to retrieve time-domain signals. Typically, spectrogram inversion is…

Speech separation is a fundamental task in audio processing, typically addressed with fully supervised systems trained on paired mixtures. While effective, such systems typically rely on synthetic data pipelines, which may not reflect…

A fairly straightforward approach for music source separation is to train independent models, wherein each model is dedicated for estimating only a specific source. Training a single model to estimate multiple sources generally does not…

Speech separation seeks to isolate individual speech signals from a multi-talk speech mixture. Despite much progress, a system well-trained on synthetic data often experiences performance degradation on out-of-domain data, such as…

In recent years time domain speech separation has excelled over frequency domain separation in single channel scenarios and noise-free environments. In this paper we dissect the gains of the time-domain audio separation network (TasNet)…

Speech Super-Resolution (SSR) is a task of enhancing low-resolution speech signals by restoring missing high-frequency components. Conventional approaches typically reconstruct log-mel features, followed by a vocoder that generates…

For supervised speech enhancement, contextual information is important for accurate spectral mapping. However, commonly used deep neural networks (DNNs) are limited in capturing temporal contexts. To leverage long-term contexts for tracking…

Neural network-based vocoders have recently demonstrated the powerful ability to synthesize high-quality speech. These models usually generate samples by conditioning on spectral features, such as Mel-spectrogram and fundamental frequency,…

The rising interest in single-channel multi-speaker speech separation sparked development of End-to-End (E2E) approaches to multi-speaker speech recognition. However, up until now, state-of-the-art neural network-based time domain source…

Image segmentation is a fundamental task in image analysis and clinical practice. The current state-of-the-art techniques are based on U-shape type encoder-decoder networks with skip connections, called U-Net. Despite the powerful…

Diffusion models, emerging as powerful deep generative tools, excel in various applications. They operate through a two-steps process: introducing noise into training samples and then employing a model to convert random noise into new…

Speaker extraction is to extract a target speaker's voice from multi-talker speech. It simulates humans' cocktail party effect or the selective listening ability. The prior work mostly performs speaker extraction in frequency domain, then…