相关论文: Cross-modal Audio-visual Co-learning for Text-inde…

Pre-trained Vision-Language Models (VLMs), like CLIP, exhibit strong generalization ability to downstream tasks but struggle in few-shot scenarios. Existing prompting techniques primarily focus on global text and image representations, yet…

Visual Speech Recognition (VSR) stands at the intersection of computer vision and speech recognition, aiming to interpret spoken content from visual cues. A prominent challenge in VSR is the presence of homophenes-visually similar lip…

This paper introduces an audio-visual speech enhancement system that leverages score-based generative models, also known as diffusion models, conditioned on visual information. In particular, we exploit audio-visual embeddings obtained from…

Multimodal deep learning systems which employ multiple modalities like text, image, audio, video, etc., are showing better performance in comparison with individual modalities (i.e., unimodal) systems. Multimodal machine learning involves…

Learning from multiple modalities, such as audio and video, offers opportunities for leveraging complementary information, enhancing robustness, and improving contextual understanding and performance. However, combining such modalities…

During the preceding biennium, vision-language pre-training has achieved noteworthy success on several downstream tasks. Nevertheless, acquiring high-quality image-text pairs, where the pairs are entirely exclusive of each other, remains a…

End-to-end Large Speech Language Models (LSLMs) have demonstrated impressive conversational generation abilities, yet consistently fall short of traditional pipeline systems on semantic understanding benchmarks. In this work, we reveal…

The success of speech-image retrieval relies on establishing an effective alignment between speech and image. Existing methods often model cross-modal interaction through simple cosine similarity of the global feature of each modality,…

While automatic speech recognition (ASR) systems degrade significantly in noisy environments, audio-visual speech recognition (AVSR) systems aim to complement the audio stream with noise-invariant visual cues and improve the system's…

Large Vision Language Models (LVLMs) have demonstrated impressive zero-shot capabilities in various vision-language dialogue scenarios. However, the absence of fine-grained visual object detection hinders the model from understanding the…

Recent Multimodal Large Language Models (MLLMs) have typically focused on integrating visual and textual modalities, with less emphasis placed on the role of speech in enhancing interaction. However, speech plays a crucial role in…

In recent years, there have been numerous developments towards solving multimodal tasks, aiming to learn a stronger representation than through a single modality. Certain aspects of the data can be particularly useful in this case - for…

Prompt learning has become one of the most efficient paradigms for adapting large pre-trained vision-language models to downstream tasks. Current state-of-the-art methods, like CoOp and ProDA, tend to adopt soft prompts to learn an…

Lipreading has a lot of potential applications such as in the domain of surveillance and video conferencing. Despite this, most of the work in building lipreading systems has been limited to classifying silent videos into classes…

There has been a long-standing quest for a unified audio-visual-text model to enable various multimodal understanding tasks, which mimics the listening, seeing and reading process of human beings. Humans tends to represent knowledge using…

Speech enhancement and speech separation are two related tasks, whose purpose is to extract either one or more target speech signals, respectively, from a mixture of sounds generated by several sources. Traditionally, these tasks have been…

Adapter-based parameter-efficient transfer learning has achieved exciting results in vision-language models. Traditional adapter methods often require training or fine-tuning, facing challenges such as insufficient samples or resource…

We introduce the visual acoustic matching task, in which an audio clip is transformed to sound like it was recorded in a target environment. Given an image of the target environment and a waveform for the source audio, the goal is to…

The audio-visual speech fusion strategy AV Align has shown significant performance improvements in audio-visual speech recognition (AVSR) on the challenging LRS2 dataset. Performance improvements range between 7% and 30% depending on the…

Aligning signals from different modalities is an important step in vision-language representation learning as it affects the performance of later stages such as cross-modality fusion. Since image and text typically reside in different…