Related papers: MiLorE-SSL: Scaling Multilingual Capabilities in S…

Self-supervised learning (SSL) is a powerful technique for learning from unlabeled data. By learning to remain invariant to applied data augmentations, methods such as SimCLR and MoCo can reach quality on par with supervised approaches.…

Self-supervised learning (SSL) has garnered significant attention in speech processing, excelling in linguistic tasks such as speech recognition. However, jointly improving the performance of pre-trained models on various downstream tasks,…

Multilingual speech recognition for both monolingual and code-switching speech is a challenging task. Recently, based on the Mixture of Experts (MoE), many works have made good progress in multilingual and code-switching ASR, but present…

Large Language Models (LLMs) have achieved remarkable results. However, existing models are expensive to train and deploy, and it is also difficult to expand their knowledge beyond pre-training data without forgetting previous knowledge.…

Self-supervised learning (SSL) representation for speech has achieved state-of-the-art (SOTA) performance on several downstream tasks. However, there remains room for improvement in speech enhancement (SE) tasks. In this study, we used a…

Self-supervised learning (SSL) models have shown exceptional capabilities across various speech-processing tasks. Continuous SSL representations are effective but suffer from high computational and storage demands. On the other hand,…

In this paper, we introduce a speech-conditioned Large Language Model (LLM) integrated with a Mixture of Experts (MoE) based connector to address the challenge of Code-Switching (CS) in Automatic Speech Recognition (ASR). Specifically, we…

Reinforcement learning (RL) with verifiable rewards (RLVR) has demonstrated the great potential of enhancing the reasoning abilities in multimodal large language models (MLLMs). However, the reliance on language-centric priors and expensive…

Code-switching (CS) is common in daily conversations where more than one language is used within a sentence. The difficulties of CS speech recognition lie in alternating languages and the lack of transcribed data. Therefore, this paper uses…

Mixture-of-experts (MoE) models facilitate efficient scaling; however, training the router network introduces the challenge of optimizing a non-differentiable, discrete objective. Recently, a fully-differentiable MoE architecture, SMEAR,…

Semi-supervised learning (SSL) has witnessed remarkable progress, resulting in the emergence of numerous method variations. However, practitioners often encounter challenges when attempting to deploy these methods due to their subpar…

Mixture-of-Experts (MoE) has emerged as a powerful framework for multi-task learning (MTL). However, existing MoE-MTL methods often rely on single-task pretrained backbones and suffer from redundant adaptation and inefficient knowledge…

Self-Supervised Learning (SSL) has emerged as the solution of choice to learn transferable representations from unlabeled data. However, SSL requires to build samples that are known to be semantically akin, i.e. positive views. Requiring…

Sparse autoencoders (SAEs) provide a powerful mechanism for decomposing the dense representations produced by Large Language Models (LLMs) into interpretable latent features. We posit that SAEs constitute a natural foundation for Learned…

End-to-end training of Spoken Language Models (SLMs) commonly involves adapting pre-trained text-based Large Language Models (LLMs) to the speech modality through multi-stage training on diverse tasks such as ASR, TTS and spoken question…

Self-supervised learning (SSL) has grown in interest within the speech processing community, since it produces representations that are useful for many downstream tasks. SSL uses global and contextual methods to produce robust…

Self-supervised learning (SSL) has emerged as a central paradigm for training foundation models by leveraging large-scale unlabeled datasets, often producing representations with strong generalization capabilities. These models are…

Recently, researchers have shown an increasing interest in automatically predicting the subjective evaluation for speech synthesis systems. This prediction is a challenging task, especially on the out-of-domain test set. In this paper, we…

Self-supervised Learning (SSL) including the mainstream contrastive learning has achieved great success in learning visual representations without data annotations. However, most of methods mainly focus on the instance level information…

Self-supervised learning (SSL) has emerged as a powerful technique for learning rich representations from unlabeled data. The data representations are able to capture many underlying attributes of data, and be useful in downstream…