相关论文: Scaling Audio-Text Retrieval with Multimodal Large…

Deriving multimodal representations of audio and lexical inputs is a central problem in Natural Language Understanding (NLU). In this paper, we present Contrastive Aligned Audio-Language Multirate and Multimodal Representations (CALM), an…

With the rapid advancement of multimodal information retrieval, increasingly complex retrieval tasks have emerged. Existing methods predominately rely on task-specific fine-tuning of vision-language models, often those trained with…

As multimodal content continues to expand at a rapid pace, audio retrieval has emerged as a key enabling technology for media search, content organization, and intelligent assistants. However, most existing benchmarks concentrate on…

Recent Large Audio-Language Models (LALMs) exhibit impressive capabilities in understanding audio content for conversational QA tasks. However, these models struggle to accurately understand timestamps for temporal localization (e.g.,…

We recently developed SLM, a joint speech and language model, which fuses a pretrained foundational speech model and a large language model (LLM), while preserving the in-context learning capability intrinsic to the pretrained LLM. In this…

Multi-modal large language models (MLLMs) have been shown to efficiently integrate natural language with visual information to handle multi-modal tasks. However, MLLMs still face a fundamental limitation of hallucinations, where they tend…

Recent multimodal embedding approaches leveraging multimodal large language models (MLLMs) fine-tuned with contrastive learning (CL) have shown promising results, yet the underlying reasons behind their superiority remain underexplored.…

Music similarity retrieval is fundamental for managing and exploring relevant content from large collections in streaming platforms. This paper presents a novel cross-modal contrastive learning framework that leverages the open-ended nature…

Multi-modal contrastive learning techniques in the audio-text domain have quickly become a highly active area of research. Most works are evaluated with standard audio retrieval and classification benchmarks assuming that (i) these models…

Large language models (LLMs) have achieved remarkable success in the field of natural language processing, enabling better human-computer interaction using natural language. However, the seamless integration of speech signals into LLMs has…

The development of Large Speech-Language Models (LSLMs) has been slowed by fragmented architectures and a lack of transparency, hindering the systematic comparison and reproducibility of research. Unlike in the vision-language domain, the…

In this paper, we propose an end-to-end Retrieval-Augmented Visual Language Model (REVEAL) that learns to encode world knowledge into a large-scale memory, and to retrieve from it to answer knowledge-intensive queries. REVEAL consists of…

Language-audio joint representation learning frameworks typically depend on deterministic embeddings, assuming a one-to-one correspondence between audio and text. In real-world settings, however, the language-audio relationship is…

We introduce AudioPaLM, a large language model for speech understanding and generation. AudioPaLM fuses text-based and speech-based language models, PaLM-2 [Anil et al., 2023] and AudioLM [Borsos et al., 2022], into a unified multimodal…

Multimodal Large Language Models (MLLMs) have achieved remarkable progress in vision-language understanding, yet how they internally integrate visual and textual information remains poorly understood. To bridge this gap, we perform a…

Audio is essential for multimodal video understanding. On the one hand, video inherently contains audio, which supplies complementary information to vision. Besides, video large language models (Video-LLMs) can encounter many audio-centric…

Music captioning has gained significant attention in the wake of the rising prominence of streaming media platforms. Traditional approaches often prioritize either the audio or lyrics aspect of the music, inadvertently ignoring the…

Despite recent progress in text-to-audio (TTA) generation, we show that the state-of-the-art models, such as AudioLDM, trained on datasets with an imbalanced class distribution, such as AudioCaps, are biased in their generation performance.…

Recent research shows a big convergence in model architecture, training objectives, and inference methods across various tasks for different modalities. In this paper, we propose VioLA, a single auto-regressive Transformer decoder-only…

The goal of audio captioning is to translate input audio into its description using natural language. One of the problems in audio captioning is the lack of training data due to the difficulty in collecting audio-caption pairs by crawling…