相关论文: NBC2: Multichannel Speech Separation with Revised …

Audio-visual speech separation methods aim to integrate different modalities to generate high-quality separated speech, thereby enhancing the performance of downstream tasks such as speech recognition. Most existing state-of-the-art (SOTA)…

Recently studies on time-domain audio separation networks (TasNets) have made a great stride in speech separation. One of the most representative TasNets is a network with a dual-path segmentation approach. However, the original model…

Although end-to-end neural text-to-speech (TTS) methods (such as Tacotron2) are proposed and achieve state-of-the-art performance, they still suffer from two problems: 1) low efficiency during training and inference; 2) hard to model long…

This paper proposes a low algorithmic latency adaptation of the deep clustering approach to speaker-independent speech separation. It consists of three parts: a) the usage of long-short-term-memory (LSTM) networks instead of their…

Convolutional neural networks (CNN) and Transformer have wildly succeeded in multimedia applications. However, more effort needs to be made to harmonize these two architectures effectively to satisfy speech enhancement. This paper aims to…

The crux of single-channel speech separation is how to encode the mixture of signals into such a latent embedding space that the signals from different speakers can be precisely separated. Existing methods for speech separation either…

We introduce CrossNet, a complex spectral mapping approach to speaker separation and enhancement in reverberant and noisy conditions. The proposed architecture comprises an encoder layer, a global multi-head self-attention module, a…

We present an efficient speech separation neural network, ARFDCN, which combines dilated convolutions, multi-scale fusion (MSF), and channel attention to overcome the limited receptive field of convolution-based networks and the high…

This study investigates phase reconstruction for deep learning based monaural talker-independent speaker separation in the short-time Fourier transform (STFT) domain. The key observation is that, for a mixture of two sources, with their…

We propose a generalized convolutional neural network (CNN) architecture that first decomposes the input signal into subbands by an adaptive filter bank structure, and then uses convolutional layers to extract features from each subband…

In a multi-channel separation task with multiple speakers, we aim to recover all individual speech signals from the mixture. In contrast to single-channel approaches, which rely on the different spectro-temporal characteristics of the…

Various neural network architectures have been proposed in recent years for the task of multi-channel speech separation. Among them, the filter-and-sum network (FaSNet) performs end-to-end time-domain filter-and-sum beamforming and has…

Recurrent Neural Networks (RNNs) have long been the dominant architecture in sequence-to-sequence learning. RNNs, however, are inherently sequential models that do not allow parallelization of their computations. Transformers are emerging…

Recently, deep clustering (DPCL) based speaker-independent speech separation has drawn much attention, since it needs little speaker prior information. However, it still has much room of improvement, particularly in reverberant…

Deep learning based speech enhancement in the short-time Fourier transform (STFT) domain typically uses a large window length such as 32 ms. A larger window can lead to higher frequency resolution and potentially better enhancement. This…

This paper proposes an end-to-end approach for single-channel speaker-independent multi-speaker speech separation, where time-frequency (T-F) masking, the short-time Fourier transform (STFT), and its inverse are represented as layers within…

Target speaker extraction aims at extracting the target speaker from a mixture of multiple speakers exploiting auxiliary information about the target speaker. In this paper, we consider a complete time-domain target speaker extraction…

Recently, our proposed recurrent neural network (RNN) based all deep learning minimum variance distortionless response (ADL-MVDR) beamformer method yielded superior performance over the conventional MVDR by replacing the matrix inversion…

We propose mixture to mixture (M2M) training, a weakly-supervised neural speech separation algorithm that leverages close-talk mixtures as a weak supervision for training discriminative models to separate far-field mixtures. Our idea is…

In this paper, we present RT-GCC-NMF: a real-time (RT), two-channel blind speech enhancement algorithm that combines the non-negative matrix factorization (NMF) dictionary learning algorithm with the generalized cross-correlation (GCC)…