相关论文: D4AM: A General Denoising Framework for Downstream…

The ultimate aim of image restoration like denoising is to find an exact correlation between the noisy and clear image domains. But the optimization of end-to-end denoising learning like pixel-wise losses is performed in a sample-to-sample…

Automatic Speech Recognition (ASR) systems must be robust to the myriad types of noises present in real-world environments including environmental noise, room impulse response, special effects as well as attacks by malicious actors…

It has been shown that the intelligibility of noisy speech can be improved by speech enhancement algorithms. However, speech enhancement has not been established as an effective frontend for robust automatic speech recognition (ASR) in…

It is an effective way that improves the performance of the existing Automatic Speech Recognition (ASR) systems by retraining with more and more new training data in the target domain. Recently, Deep Neural Network (DNN) has become a…

Speech enhancement (SE) is used as a frontend in speech applications including automatic speech recognition (ASR) and telecommunication. A difficulty in using the SE frontend is that the appropriate noise reduction level differs depending…

Background noise is a major source of quality impairments in Voice over Internet Protocol (VoIP) and Public Switched Telephone Network (PSTN) calls. Recent work shows the efficacy of deep learning for noise suppression, but the datasets…

Speech audio quality is subject to degradation caused by an acoustic environment and isotropic ambient and point noises. The environment can lead to decreased speech intelligibility and loss of focus and attention by the listener. Basic…

The generalization performance of deep neural networks (DNNs) is a critical factor in achieving robust model behavior on unseen data. Recent studies have highlighted the importance of sharpness-based measures in promoting generalization by…

This report proposes a polyphonic sound event detection (SED) method for the DCASE 2021 Challenge Task 4. The proposed SED model consists of two stages: a mean-teacher model for providing target labels regarding weakly labeled or unlabeled…

Synthetic aperture radar automatic target recognition (SAR ATR) is of considerable importance in marine navigation and disaster monitoring. However, the coherent speckle noise inherent in SAR imagery often obscures salient target features,…

Diffusion models have become a leading paradigm in generative AI, with score estimation via denoising score matching as a central component. While recent theory provides strong statistical guarantees, it typically relies on…

Automatic speech recognition systems are part of people's daily lives, embedded in personal assistants and mobile phones, helping as a facilitator for human-machine interaction while allowing access to information in a practically intuitive…

We present a frontend for improving robustness of automatic speech recognition (ASR), that jointly implements three modules within a single model: acoustic echo cancellation, speech enhancement, and speech separation. This is achieved by…

Noisy training data can significantly degrade the performance of language-model-based classifiers, particularly in non-topical classification tasks. In this study we designed a methodological framework to assess the impact of denoising.…

Lately, the self-attention mechanism has marked a new milestone in the field of automatic speech recognition (ASR). Nevertheless, its performance is susceptible to environmental intrusions as the system predicts the next output symbol…

We propose a novel approach to semi-supervised automatic speech recognition (ASR). We first exploit a large amount of unlabeled audio data via representation learning, where we reconstruct a temporal slice of filterbank features from past…

While the deep learning techniques promote the rapid development of the speech enhancement (SE) community, most schemes only pursue the performance in a black-box manner and lack adequate model interpretability. Inspired by Taylor's…

Generative AI has received significant attention among a spectrum of diverse industrial and academic domains, thanks to the magnificent results achieved from deep generative models such as generative pre-trained transformers (GPT) and…

Segment Anything Models (SAMs), known for their exceptional zero-shot segmentation performance, have garnered significant attention in the research community. Nevertheless, their performance drops significantly on severely degraded,…

Diffusion magnetic resonance imaging datasets suffer from low Signal-to-Noise Ratio, especially at high b-values. Acquiring data at high b-values contains relevant information and is now of great interest for microstructural and…