相关论文: Components Loss for Neural Networks in Mask-Based …

In this paper, we propose VoiceID loss, a novel loss function for training a speech enhancement model to improve the robustness of speaker verification. In contrast to the commonly used loss functions for speech enhancement such as the L2…

Latent representation learned from multi-layered neural networks via hierarchical feature abstraction enables recent success of deep learning. Under the deep learning framework, generalization performance highly depends on the learned…

This paper proposes a Convolutional Neural Network (CNN) inspired by Multitask Learning (MTL) and based on speech features trained under the joint supervision of softmax loss and center loss, a powerful metric learning strategy, for the…

Complex-valued processing has brought deep learning-based speech enhancement and signal extraction to a new level. Typically, the process is based on a time-frequency (TF) mask which is applied to a noisy spectrogram, while complex masks…

Convolutional neural networks (CNNs) with residual links (ResNets) and causal dilated convolutional units have been the network of choice for deep learning approaches to speech enhancement. While residual links improve gradient flow during…

Real-time speech enhancement (SE) is essential to online speech communication. Causal SE models use only the previous context while predicting future information, such as phoneme continuation, may help performing causal SE. The phonetic…

Acoustic echo cancellation (AEC) plays an important role in the full-duplex speech communication as well as the front-end speech enhancement for recognition in the conditions when the loudspeaker plays back. In this paper, we present an…

Usually, hearing impaired people use hearing aids which are implemented with speech enhancement algorithms. Estimation of speech and estimation of nose are the components in single channel speech enhancement system. The main objective of…

Consistency regularization has prevailed in semi-supervised semantic segmentation and achieved promising performance. However, existing methods typically concentrate on enhancing the Image-augmentation based Prediction consistency and…

This paper aims to address two issues existing in the current speech enhancement methods: 1) the difficulty of phase estimations; 2) a single objective function cannot consider multiple metrics simultaneously. To solve the first problem, we…

Recently, phase processing is attracting increasinginterest in speech enhancement community. Some researchersintegrate phase estimations module into speech enhancementmodels by using complex-valued short-time Fourier transform(STFT)…

Continual Learning (CL) aims to enable models to sequentially learn multiple tasks without forgetting previous knowledge. Recent studies have shown that optimizing towards flatter loss minima can improve model generalization. However,…

The ability to remove features from the input of machine learning models is very important to understand and interpret model predictions. However, this is non-trivial for vision models since masking out parts of the input image typically…

This paper proposes a delayed subband LSTM network for online monaural (single-channel) speech enhancement. The proposed method is developed in the short time Fourier transform (STFT) domain. Online processing requires frame-by-frame signal…

Despite rapid advancement in recent years, current speech enhancement models often produce speech that differs in perceptual quality from real clean speech. We propose a learning objective that formalizes differences in perceptual quality,…

The increasingly stringent requirement on quality-of-experience in 5G/B5G communication systems has led to the emerging neural speech enhancement techniques, which however have been developed in isolation from the existing expert-rule based…

Deep learning algorithm are increasingly used for speech enhancement (SE). In supervised methods, global and local information is required for accurate spectral mapping. A key restriction is often poor capture of key contextual information.…

In recent decades, neural network based methods have significantly improved the performace of speech enhancement. Most of them estimate time-frequency (T-F) representation of target speech directly or indirectly, then resynthesize waveform…

We propose adversarial constrained-CNN loss, a new paradigm of constrained-CNN loss methods, for weakly supervised medical image segmentation. In the new paradigm, prior knowledge is encoded and depicted by reference masks, and is further…

Speech enhancement models have greatly progressed in recent years, but still show limits in perceptual quality of their speech outputs. We propose an objective for perceptual quality based on temporal acoustic parameters. These are…