相关论文: Can LLMs Understand Unvoiced Speech? Exploring EMG…

While Multimodal Large Language Models (MLLMs) show promising performance in automated electrocardiogram interpretation, it remains unclear whether they genuinely perform actual step-by-step reasoning or just rely on superficial visual…

Masked Language Models (MLM) are self-supervised neural networks trained to fill in the blanks in a given sentence with masked tokens. Despite the tremendous success of MLMs for various text based tasks, they are not robust for spoken…

Human communication is a multifaceted and multimodal skill. Communication requires an understanding of both the surface-level textual content and the connotative intent of a piece of communication. In humans, learning to go beyond the…

Surface electromyography (sEMG) provides a direct neural interface for decoding muscle activity and offers a promising foundation for keyboard-free text input in wearable and mixed-reality systems. Previous sEMG-to-text studies mainly…

Self-Supervised Learning (SSL) has gained traction for its ability to learn rich representations with low labeling costs, applicable across diverse downstream tasks. However, assessing the downstream-task performance remains challenging due…

While speech foundation models (SFMs) have demonstrated remarkable performance in audio-only tasks, their adaptation to multimodal scenarios remains underexplored. This work presents UASR-LLM, a novel framework that adapts frozen SFMs to…

Multimodal Large Language Models (MLLMs) mimic human perception and reasoning system by integrating powerful Large Language Models (LLMs) with various modality encoders (e.g., vision, audio), positioning LLMs as the "brain" and various…

The advent of multimodal large language models (MLLMs) has sparked interest in their application to electrocardiogram (ECG) analysis. However, existing ECG-focused MLLMs primarily focus on report generation tasks, often limited to single…

While integrating speech encoder with LLM requires substantial data and resources, use cases face limitations due to insufficient availability. To address this, we propose a solution with a parameter-efficient adapter that converts speech…

Speech enhancement (SE) aims to improve the clarity, intelligibility, and quality of speech signals for various speech enabled applications. However, air-conducted (AC) speech is highly susceptible to ambient noise, particularly in low…

Current methods of building LLMs with voice interaction capabilities rely heavily on explicit text autoregressive generation before or during speech response generation to maintain content quality, which unfortunately brings computational…

Interactions with virtual assistants typically start with a trigger phrase followed by a command. In this work, we explore the possibility of making these interactions more natural by eliminating the need for a trigger phrase. Our goal is…

Multimodal Empathetic Response Generation (MERG) is crucial for building emotionally intelligent human-computer interactions. Although large language models (LLMs) have improved text-based ERG, challenges remain in handling multimodal…

Modeling the relationship between natural speech and a recorded electroencephalogram (EEG) helps us understand how the brain processes speech and has various applications in neuroscience and brain-computer interfaces. In this context, so…

Emotion recognition from electroencephalography (EEG) signals remains challenging due to high inter-subject variability, limited labeled data, and the lack of interpretable reasoning in existing approaches. While recent multimodal large…

Language model (LM) based audio generation frameworks, e.g., AudioLM, have recently achieved new state-of-the-art performance in zero-shot audio generation. In this paper, we explore the feasibility of LMs for zero-shot voice conversion. An…

Connecting audio encoders with large language models (LLMs) allows the LLM to perform various audio understanding tasks, such as automatic speech recognition (ASR) and audio captioning (AC). Most research focuses on training an adapter…

Large language models (LLMs), renowned for their powerful conversational abilities, are widely recognized as exceptional tools in the field of education, particularly in the context of automated intelligent instruction systems for language…

Target volume contouring for radiation therapy is considered significantly more challenging than the normal organ segmentation tasks as it necessitates the utilization of both image and text-based clinical information. Inspired by the…

Non-invasive decoding of imagined speech remains challenging due to weak, distributed signals and limited labeled data. Our paper introduces an image-based approach that transforms magnetoencephalography (MEG) signals into time-frequency…