Related papers: Multi-Dimensional and Multi-Scale Modeling for Spe…
The continuous speech separation (CSS) is a task to separate the speech sources from a long, partially overlapped recording, which involves a varying number of speakers. A straightforward extension of conventional utterance-level speech…
Most speech separation methods, trying to separate all channel sources simultaneously, are still far from having enough general- ization capabilities for real scenarios where the number of input sounds is usually uncertain and even dynamic.…
Recently, stunning improvements on multi-channel speech separation have been achieved by neural beamformers when direction information is available. However, most of them neglect to utilize speaker's 2-dimensional (2D) location cues…
We present an upper bound for the Single Channel Speech Separation task, which is based on an assumption regarding the nature of short segments of speech. Using the bound, we are able to show that while the recent methods have made…
We present TokenSplit, a speech separation model that acts on discrete token sequences. The model is trained on multiple tasks simultaneously: separate and transcribe each speech source, and generate speech from text. The model operates on…
Despite the recent success of speech separation models, they fail to separate sources properly while facing different sets of people or noisy environments. To tackle this problem, we proposed to apply meta-learning to the speech separation…
In recent years, rapid progress has been made on the problem of single-channel sound separation using supervised training of deep neural networks. In such supervised approaches, a model is trained to predict the component sources from…
The dominant speech separation models are based on complex recurrent or convolution neural network that model speech sequences indirectly conditioning on context, such as passing information through many intermediate states in recurrent…
Advancements in deep learning and voice-activated technologies have driven the development of human-vehicle interaction. Distributed microphone arrays are widely used in in-car scenarios because they can accurately capture the voices of…
The end-to-end approach for single-channel speech separation has been studied recently and shown promising results. This paper extended the previous approach and proposed a new end-to-end model for multi-channel speech separation. The…
Transformer has been successfully applied to speech separation recently with its strong long-dependency modeling capacity using a self-attention mechanism. However, Transformer tends to have heavy run-time costs due to the deep encoder…
Background noise, interfering speech and room reverberation frequently distort target speech in real listening environments. In this study, we address joint speech separation and dereverberation, which aims to separate target speech from…
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…
This work proposes a neural network to extensively exploit spatial information for multichannel joint speech separation, denoising and dereverberation, named SpatialNet. In the short-time Fourier transform (STFT) domain, the proposed…
Target speech extraction (TSE) systems are designed to extract target speech from a multi-talker mixture. The popular training objective for most prior TSE networks is to enhance reconstruction performance of extracted speech waveform.…
Training speech separation models in the supervised setting raises a permutation problem: finding the best assignation between the model predictions and the ground truth separated signals. This inherently ambiguous task is customarily…
Speech separation has been successfully applied as a frontend processing module of conversation transcription systems thanks to its ability to handle overlapped speech and its flexibility to combine with downstream tasks such as automatic…
Hand-crafted spatial features (e.g., inter-channel phase difference, IPD) play a fundamental role in recent deep learning based multi-channel speech separation (MCSS) methods. However, these manually designed spatial features are hard to…
With the development of teleconferencing and in-vehicle voice assistants, far-field multi-speaker speech recognition has become a hot research topic. Recently, a multi-channel transformer (MCT) has been proposed, which demonstrates the…
Speaker extraction (SE) aims to segregate the speech of a target speaker from a mixture of interfering speakers with the help of auxiliary information. Several forms of auxiliary information have been employed in single-channel SE, such as…