Related papers: MeanFlowSE: One-Step Generative Speech Enhancement…
This paper addresses unsupervised diffusion-based single-channel speech enhancement (SE). Prior work in this direction combines a score-based diffusion model trained on clean speech with a Gaussian noise model whose covariance is structured…
We propose Speech Enhancement based on Drifting Models (DriftSE), a novel generative framework that formulates denoising as an equilibrium problem. Rather than relying on iterative sampling, DriftSE natively achieves one-step inference by…
Generative target speaker extraction (TSE) methods often produce more natural outputs than predictive models. Recent work based on diffusion or flow matching (FM) typically relies on a small, fixed number of reverse steps with a fixed step…
Real-world speech recordings suffer from degradations such as background noise and reverberation. Speech enhancement aims to mitigate these issues by generating clean high-fidelity signals. While recent generative approaches for speech…
Recent research has delved into speech enhancement (SE) approaches that leverage audio embeddings from pre-trained models, diverging from time-frequency masking or signal prediction techniques. This paper introduces an efficient and…
Speech enhancement (SE) based on diffusion probabilistic models has exhibited impressive performance, while requiring a relatively high number of function evaluations (NFE). Recently, SE based on flow matching has been proposed, which…
Automatic speech recognition (ASR) has gained remarkable successes thanks to recent advances of deep learning, but it usually degrades significantly under real-world noisy conditions. Recent works introduce speech enhancement (SE) as…
Current pre-training works in natural language generation pay little attention to the problem of exposure bias on downstream tasks. To address this issue, we propose an enhanced multi-flow sequence to sequence pre-training and fine-tuning…
Recent studies demonstrate the effectiveness of Self Supervised Learning (SSL) speech representations for Speech Inversion (SI). However, applying SI in real-world scenarios remains challenging due to the pervasive presence of background…
Conventional deep neural network (DNN)-based speech enhancement (SE) approaches aim to minimize the mean square error (MSE) between enhanced speech and clean reference. The MSE-optimized model may not directly improve the performance of an…
This paper presents a generative approach to speech enhancement based on a recurrent variational autoencoder (RVAE). The deep generative speech model is trained using clean speech signals only, and it is combined with a nonnegative matrix…
Target speaker extraction (TSE) extracts the target speaker's voice from overlapping speech mixtures given a reference utterance. Existing approaches typically fall into two categories: discriminative and generative. Discriminative methods…
Deploying speech enhancement (SE) systems in wearable devices, such as smart glasses, is challenging due to the limited computational resources on the device. Although deep learning methods have achieved high-quality results, their…
Speech enhancement (SE) is usually required as a front end to improve the speech quality in noisy environments, while the enhanced speech might not be optimal for automatic speech recognition (ASR) systems due to speech distortion. On the…
Generative models have shown robust performance on speech enhancement and restoration tasks, but most prior approaches operate offline with high latency, making them unsuitable for streaming applications. In this work, we investigate the…
Generative models have shown great potential in trajectory planning. Recent studies demonstrate that anchor-guided generative models are effective in modeling the uncertainty of driving behaviors and improving overall performance. However,…
Target speaker extraction (TSE) aims to recover the speech of a desired speaker from a mixture given a short enrollment utterance, while speech enhancement (SE) focuses on improving speech quality under noisy conditions. Most existing TSE…
Target speaker extraction (TSE) aims to isolate a specific speaker's speech from a mixture using speaker enrollment as a reference. While most existing approaches are discriminative, recent generative methods for TSE achieve strong results.…
The human brain contextually exploits heterogeneous sensory information to efficiently perform cognitive tasks including vision and hearing. For example, during the cocktail party situation, the human auditory cortex contextually integrates…
Recent speech enhancement (SE) models increasingly leverage self-supervised learning (SSL) representations for their rich semantic information. Typically, intermediate features are aggregated into a single representation via a lightweight…