Related papers: Multi-channel Speech Separation Using Deep Embeddi…

Most deep learning-based multi-channel speech enhancement methods focus on designing a set of beamforming coefficients to directly filter the low signal-to-noise ratio signals received by microphones, which hinders the performance of these…

Speech enhancement and separation are two fundamental tasks for robust speech processing. Speech enhancement suppresses background noise while speech separation extracts target speech from interfering speakers. Despite a great number of…

Under noisy environments, to achieve the robust performance of speaker recognition is still a challenging task. Motivated by the promising performance of multi-task training in a variety of image processing tasks, we explore the potential…

Conversation disentanglement aims to group utterances into detached sessions, which is a fundamental task in processing multi-party conversations. Existing methods have two main drawbacks. First, they overemphasize pairwise utterance…

The objective of deep learning methods based on encoder-decoder architectures for music source separation is to approximate either ideal time-frequency masks or spectral representations of the target music source(s). The spectral…

Training deep neural networks(DNN) with noisy labels is challenging since DNN can easily memorize inaccurate labels, leading to poor generalization ability. Recently, the meta-learning based label correction strategy is widely adopted to…

Domain mismatch problem caused by speaker-unrelated feature has been a major topic in speaker recognition. In this paper, we propose an explicit disentanglement framework to unravel speaker-relevant features from speaker-unrelated features…

We investigate the effectiveness of convolutive prediction, a novel formulation of linear prediction for speech dereverberation, for speaker separation in reverberant conditions. The key idea is to first use a deep neural network (DNN) to…

Deep learning-based works for singing voice separation have performed exceptionally well in the recent past. However, most of these works do not focus on allowing users to interact with the model to improve performance. This can be crucial…

This paper introduces a practical approach for leveraging a real-time deep learning model to alternate between speech enhancement and joint speech enhancement and separation depending on whether the input mixture contains one or two active…

The dual-path RNN (DPRNN) was proposed to more effectively model extremely long sequences for speech separation in the time domain. By splitting long sequences to smaller chunks and applying intra-chunk and inter-chunk RNNs, the DPRNN…

Speech-related applications deliver inferior performance in complex noise environments. Therefore, this study primarily addresses this problem by introducing speech-enhancement (SE) systems based on deep neural networks (DNNs) applied to a…

Speech enhancement and speech separation are two related tasks, whose purpose is to extract either one or more target speech signals, respectively, from a mixture of sounds generated by several sources. Traditionally, these tasks have been…

This paper proposes a unified deep speaker embedding framework for modeling speech data with different sampling rates. Considering the narrowband spectrogram as a sub-image of the wideband spectrogram, we tackle the joint modeling problem…

In this study, we propose a modulation decoupling based single channel speech enhancement subspace framework, in which the spectrogram of noisy speech is decoupled as the product of a spectral envelop subspace and a spectral details…

Deep neural networks (DNN) techniques have become pervasive in domains such as natural language processing and computer vision. They have achieved great success in these domains in task such as machine translation and image generation. Due…

The performance of most speaker diarization systems with x-vector embeddings is both vulnerable to noisy environments and lacks domain robustness. Earlier work on speaker diarization using generative adversarial network (GAN) with an…

In this paper, we address the problem of speaker recognition in challenging acoustic conditions using a novel method to extract robust speaker-discriminative speech representations. We adopt a recently proposed unsupervised adversarial…

Recording channel mismatch between training and testing conditions has been shown to be a serious problem for speech separation. This situation greatly reduces the separation performance, and cannot meet the requirement of daily use. In…

Multi-channel speech enhancement seeks to utilize spatial information to distinguish target speech from interfering signals. While deep learning approaches like the dual-path convolutional recurrent network (DPCRN) have made strides,…