Related papers: deHuBERT: Disentangling Noise in a Self-supervised…

Large-scale speech self-supervised learning (SSL) has emerged to the main field of speech processing, however, the problem of computational cost arising from its vast size makes a high entry barrier to academia. In addition, existing…

This paper studies a novel pre-training technique with unpaired speech data, Speech2C, for encoder-decoder based automatic speech recognition (ASR). Within a multi-task learning framework, we introduce two pre-training tasks for the…

Speech-enabled systems typically first convert audio to text through an automatic speech recognition (ASR) model and then feed the text to downstream natural language processing (NLP) modules. The errors of the ASR system can seriously…

In realistic environments, speech is usually interfered by various noise and reverberation, which dramatically degrades the performance of automatic speech recognition (ASR) systems. To alleviate this issue, the commonest way is to use a…

We present a general framework for designing efficient algorithms for unsupervised learning problems, such as mixtures of Gaussians and subspace clustering. Our framework is based on a meta algorithm that learns arithmetic circuits in the…

ConvNets achieve good results when training from clean data, but learning from noisy labels significantly degrades performances and remains challenging. Unlike previous works constrained by many conditions, making them infeasible to real…

Image noise modeling is a long-standing problem with many applications in computer vision. Early attempts that propose simple models, such as signal-independent additive white Gaussian noise or the heteroscedastic Gaussian noise model…

Self-supervised learned (SSL) models such as Wav2vec and HuBERT yield state-of-the-art results on speech-related tasks. Given the effectiveness of such models, it is advantageous to use them in conventional ASR systems. While some…

Deep learning had already demonstrated its power in medical images, including denoising, classification, segmentation, etc. All these applications are proposed to automatically analyze medical images beforehand, which brings more…

Traditional denoising methods for noise removal have largely relied on handcrafted priors, often perform well in controlled environments but struggle to address the complexity and variability of real noise. In contrast, deep learning-based…

The quality of audio recordings in outdoor environments is often degraded by the presence of wind. Mitigating the impact of wind noise on the perceptual quality of single-channel speech remains a significant challenge due to its…

Speech is the surface form of a finite set of phonetic units, which can be represented by discrete codes. We propose the Code BERT (CoBERT) approach for self-supervised speech representation learning. The idea is to convert an utterance to…

With its significant performance improvements, the deep learning paradigm has become a standard tool for modern image denoisers. While promising performance has been shown on seen noise distributions, existing approaches often suffer from…

We create a reusable Transformer, BrainBERT, for intracranial recordings bringing modern representation learning approaches to neuroscience. Much like in NLP and speech recognition, this Transformer enables classifying complex concepts,…

Noise-robust speaker verification leverages joint learning of speech enhancement (SE) and speaker verification (SV) to improve robustness. However, prevailing approaches rely on implicit noise suppression, which struggles to separate noise…

The paradigm of learning from automatic annotations driven by pre-trained experts and Foundation Models dominates data-hungry applications. However, it introduces a critical challenge: model-induced label noise. Unlike stochastic noise in…

Many studies have shown various biases targeting different demographic groups in language models, amplifying discrimination and harming fairness. Recent parameter modification debiasing approaches significantly degrade core capabilities…

Self-supervised learning (SSL) has achieved notable success in many speech processing tasks, but the large model size and heavy computational cost hinder the deployment. Knowledge distillation trains a small student model to mimic the…

Word embeddings have been demonstrated to benefit NLP tasks impressively. Yet, there is room for improvement in the vector representations, because current word embeddings typically contain unnecessary information, i.e., noise. We propose…

Speech recognition in noisy and channel distorted scenarios is often challenging as the current acoustic modeling schemes are not adaptive to the changes in the signal distribution in the presence of noise. In this work, we develop a novel…