Related papers: DPCCN: Densely-Connected Pyramid Complex Convoluti…

Audio-visual multi-modal modeling has been demonstrated to be effective in many speech related tasks, such as speech recognition and speech enhancement. This paper introduces a new time-domain audio-visual architecture for target speaker…

In recent years there have been many deep learning approaches towards the multi-speaker source separation problem. Most use Long Short-Term Memory - Recurrent Neural Networks (LSTM-RNN) or Convolutional Neural Networks (CNN) to model the…

Binaural speech enhancement (BSE) aims to jointly improve the speech quality and intelligibility of noisy signals received by hearing devices and preserve the spatial cues of the target for natural listening. Existing methods often suffer…

We propose TF-GridNet for speech separation. The model is a novel deep neural network (DNN) integrating full- and sub-band modeling in the time-frequency (T-F) domain. It stacks several blocks, each consisting of an intra-frame full-band…

Speech separation in realistic acoustic environments remains challenging because overlapping speakers, background noise, and reverberation must be resolved simultaneously. Although recent time-frequency (TF) domain models have shown strong…

Feature mapping using deep neural networks is an effective approach for single-channel speech enhancement. Noisy features are transformed to the enhanced ones through a mapping network and the mean square errors between the enhanced and…

Speech enhancement techniques based on deep learning have brought significant improvement on speech quality and intelligibility. Nevertheless, a large gain in speech quality measured by objective metrics, such as perceptual evaluation of…

Acoustic echo and background noise can seriously degrade the intelligibility of speech. In practice, echo and noise suppression are usually treated as two separated tasks and can be removed with various digital signal processing (DSP) and…

Singing voice separation and vocal pitch estimation are pivotal tasks in music information retrieval. Existing methods for simultaneous extraction of clean vocals and vocal pitches can be classified into two categories: pipeline methods and…

In this paper, we present a novel diffusion model-based monaural speech enhancement method. Our approach incorporates the separate estimation of speech spectra's magnitude and phase in two diffusion networks. Throughout the diffusion…

Large-scale pre-trained self-supervised learning (SSL) models have shown remarkable advancements in speech-related tasks. However, the utilization of these models in complex multi-talker scenarios, such as extracting a target speaker in a…

Time-frequency masking or spectrum prediction computed via short symmetric windows are commonly used in low-latency deep neural network (DNN) based source separation. In this paper, we propose the usage of an asymmetric analysis-synthesis…

In this work, we propose Exformer, a time-domain architecture for target speaker extraction. It consists of a pre-trained speaker embedder network and a separator network based on transformer encoder blocks. We study multiple methods to…

In recent years, waveform-mapping-based speech enhancement (SE) methods have garnered significant attention. These methods generally use a deep learning model to directly process and reconstruct speech waveforms. Because both the input and…

Despite the recent success of deep learning for many speech processing tasks, single-microphone, speaker-independent speech separation remains challenging for two main reasons. The first reason is the arbitrary order of the target and…

In recent years, deep learning-based single-channel speech separation has improved considerably, in large part driven by increasingly compute- and parameter-efficient neural network architectures. Most such architectures are, however,…

Speech enhancement algorithms based on deep learning have greatly surpassed their traditional counterparts and are now being considered for the task of removing acoustic echo from hands-free communication systems. This is a challenging…

Target Speaker Extraction (TSE) uses a reference cue to extract the target speech from a mixture. In TSE systems relying on audio cues, the speaker embedding from the enrolled speech is crucial to performance. However, these embeddings may…

We propose multi-microphone complex spectral mapping, a simple way of applying deep learning for time-varying non-linear beamforming, for speaker separation in reverberant conditions. We aim at both speaker separation and dereverberation.…

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…