Related papers: MAGE: A Coarse-to-Fine Speech Enhancer with Masked…

We propose a training-free approach to improve sentence embeddings leveraging test-time compute by applying generative text models for data augmentation at inference time. Unlike conventional data augmentation that utilises synthetic…

Speech enhancement (SE) is critical for improving speech intelligibility and quality in real-world environments, particularly for cochlear implant (CI) users who experience severe degradations in speech understanding under noisy and…

We introduce MARGE, a pre-trained sequence-to-sequence model learned with an unsupervised multi-lingual multi-document paraphrasing objective. MARGE provides an alternative to the dominant masked language modeling paradigm, where we…

Speech enhancement aims to obtain speech signals with high intelligibility and quality from noisy speech. Recent work has demonstrated the excellent performance of time-domain deep learning methods, such as Conv-TasNet. However, these…

Supervised speech enhancement methods have been very successful. However, in practical scenarios, there is a lack of clean speech, and self-supervised learning-based (SSL) speech enhancement methods that offer comparable enhancement…

Enhancing speech quality under adverse SNR conditions remains a significant challenge for discriminative deep neural network (DNN)-based approaches. In this work, we propose DisCoGAN, which is a time-frequency-domain generative adversarial…

Data augmentation is a valuable tool for the design of deep learning systems to overcome data limitations and stabilize the training process. Especially in the medical domain, where the collection of large-scale data sets is challenging and…

Retrieval-Augmented Generation (RAG) aims to generate more reliable and accurate responses, by augmenting large language models (LLMs) with the external vast and dynamic knowledge. Most previous work focuses on using RAG for single-round…

Short-utterance speaker verification remains challenging due to limited speaker-discriminative cues in short speech segments. While existing methods focus on enhancing speaker encoders, the embedding learning strategy still forces a single…

Retrieval-Augmented Generation (RAG) has emerged as a powerful framework to improve factuality in large language models (LLMs) by grounding their outputs in retrieved documents. However, ensuring perfect retrieval of relevant information…

This paper introduces OmniGSE, a novel general speech enhancement (GSE) framework designed to mitigate the diverse distortions that speech signals encounter in real-world scenarios. These distortions include background noise, reverberation,…

Retrieval-augmented generation (RAG) systems have been shown to be effective in addressing many of the drawbacks of relying solely on the parametric memory of large language models. Recent work has demonstrated that RAG systems can be…

Masked Autoencoders (MAE) have been popular paradigms for large-scale vision representation pre-training. However, MAE solely reconstructs the low-level RGB signals after the decoder and lacks supervision upon high-level semantics for the…

Large Language Models (LLMs) exhibit strong potential in mathematical reasoning, yet their effectiveness is often limited by a shortage of high-quality queries. This limitation necessitates scaling up computational responses through…

Speech enhancement performance degrades significantly in noisy environments, limiting the deployment of speech-controlled technologies in industrial settings, such as manufacturing plants. Existing speech enhancement solutions primarly rely…

Masked Autoencoder (MAE) has demonstrated superior performance on various vision tasks via randomly masking image patches and reconstruction. However, effective data augmentation strategies for MAE still remain open questions, different…

Masked Autoencoders (MAEs) learn rich low-level representations from unlabeled data but require substantial labeled data to effectively adapt to downstream tasks. Conversely, Instance Discrimination (ID) emphasizes high-level semantics,…

Recently, Mixture of Experts (MoE) based Transformer has shown promising results in many domains. This is largely due to the following advantages of this architecture: firstly, MoE based Transformer can increase model capacity without…

Automatic speech recognition (ASR) systems are of vital importance nowadays in commonplace tasks such as speech-to-text processing and language translation. This created the need for an ASR system that can operate in realistic crowded…

While large audio-language models have advanced open-ended audio understanding, they still fall short of nuanced human-level comprehension. This gap persists largely because current benchmarks, limited by data annotations and evaluation…