相关论文: Exploring Efficient-Tuned Learning Audio Represent…

Music performances are representative scenarios for audio-visual modeling. Unlike common scenarios with sparse audio, music performances continuously involve dense audio signals throughout. While existing multimodal learning methods on the…

Training audio-to-image generative models requires an abundance of diverse audio-visual pairs that are semantically aligned. Such data is almost always curated from in-the-wild videos, given the cross-modal semantic correspondence that is…

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…

Large language models (LLMs) have demonstrated strong instruction-following capabilities in text-based tasks. However, this ability often deteriorates in multimodal models after alignment with non-text modalities such as images or audio.…

The amount of articulatory data available for training deep learning models is much less compared to acoustic speech data. In order to improve articulatory-to-acoustic synthesis performance in these low-resource settings, we propose a…

Vision-language pre-training (VLP) on large-scale image-text pairs has recently witnessed rapid progress for learning cross-modal representations. Existing pre-training methods either directly concatenate image representation and text…

Recently, self-supervised pre-training has shown significant improvements in many areas of machine learning, including speech and NLP. We propose using large self-supervised pre-trained models for both audio and text modality with…

Large-scale pre-trained image-text models demonstrate remarkable versatility across diverse tasks, benefiting from their robust representational capabilities and effective multimodal alignment. We extend the application of these models,…

We explore self-supervised models that can be potentially deployed on mobile devices to learn general purpose audio representations. Specifically, we propose methods that exploit the temporal context in the spectrogram domain. One method…

Current methods for learning visually grounded language from videos often rely on text annotation, such as human generated captions or machine generated automatic speech recognition (ASR) transcripts. In this work, we introduce the…

Understanding videos inherently requires reasoning over both visual and auditory information. To properly evaluate Omni-Large Language Models (Omni-LLMs), which are capable of processing multi-modal information including vision and audio,…

Energy-based latent variable models (EBLVMs) are more expressive than conventional energy-based models. However, its potential on visual tasks are limited by its training process based on maximum likelihood estimate that requires sampling…

Although speech is a simple and effective way for humans to communicate with the outside world, a more realistic speech interaction contains multimodal information, e.g., vision, text. How to design a unified framework to integrate…

Although speaker verification has conventionally been an audio-only task, some practical applications provide both audio and visual streams of input. In these cases, the visual stream provides complementary information and can often be…

Recent advancements in large language models (LLMs) have significantly propelled the development of large multi-modal models (LMMs), highlighting the potential for general and intelligent assistants. However, most LMMs model visual and…

In this work, we introduce LLaDA-V, a purely diffusion-based Multimodal Large Language Model (MLLM) that integrates visual instruction tuning with masked diffusion models, representing a departure from the autoregressive paradigms dominant…

In multimedia applications such as films and video games, spatial audio techniques are widely employed to enhance user experiences by simulating 3D sound: transforming mono audio into binaural formats. However, this process is often complex…

Audio-visual representation learning is an important task from the perspective of designing machines with the ability to understand complex events. To this end, we propose a novel multimodal framework that instantiates multiple instance…

We present AdVerb, a novel audio-visual dereverberation framework that uses visual cues in addition to the reverberant sound to estimate clean audio. Although audio-only dereverberation is a well-studied problem, our approach incorporates…

Transformer-based multimodal models are widely used in industrial-scale recommendation, search, and advertising systems for content understanding and relevance ranking. Enhancing labeled training data quality and cross-modal fusion…