English
Related papers

Related papers: Audiocards: Structured Metadata Improves Audio Lan…

200 papers

Compared with ample visual-text pre-training research, few works explore audio-text pre-training, mostly due to the lack of sufficient parallel audio-text data. Most existing methods incorporate the visual modality as a pivot for audio-text…

Sound · Computer Science 2024-03-06 Xuenan Xu , Zhiling Zhang , Zelin Zhou , Pingyue Zhang , Zeyu Xie , Mengyue Wu , Kenny Q. Zhu

Recent advances in generating synthetic captions based on audio and related metadata allow using the information contained in natural language as input for other audio tasks. In this paper, we propose a novel method to guide a sound event…

Audio and Speech Processing · Electrical Eng. & Systems 2025-08-29 Manu Harju , Annamaria Mesaros

Spoofed audio, i.e. audio that is manipulated or AI-generated deepfake audio, is difficult to detect when only using acoustic features. Some recent innovative work involving AI-spoofed audio detection models augmented with phonetic and…

Sound · Computer Science 2024-10-22 Zahra Khanjani , Christine Mallinson , James Foulds , Vandana P Janeja

Developing new machine learning applications often requires the collection of new datasets. However, existing datasets may already contain relevant information to train models for new purposes. We propose SoundCollage: a framework to…

Incorporating metadata in Large Language Models (LLMs) pretraining has recently emerged as a promising approach to accelerate training. However prior work highlighted only one useful signal-URLs, leaving open the question of whether other…

Computation and Language · Computer Science 2026-04-21 Dongyang Fan , Diba Hashemi , Sai Praneeth Karimireddy , Martin Jaggi

Deep neural networks have recently achieved breakthroughs in sound generation. Despite the outstanding sample quality, current sound generation models face issues on small-scale datasets (e.g., overfitting), significantly limiting…

Sound · Computer Science 2024-07-30 Yi Yuan , Haohe Liu , Jinhua Liang , Xubo Liu , Mark D. Plumbley , Wenwu Wang

Automatic music captioning, which generates natural language descriptions for given music tracks, holds significant potential for enhancing the understanding and organization of large volumes of musical data. Despite its importance,…

Sound · Computer Science 2023-08-01 SeungHeon Doh , Keunwoo Choi , Jongpil Lee , Juhan Nam

Recent years have seen significant progress in Text-To-Audio (TTA) synthesis, enabling users to enrich their creative workflows with synthetic audio generated from natural language prompts. Despite this progress, the effects of data, model…

Sound · Computer Science 2025-07-02 Sang-gil Lee , Zhifeng Kong , Arushi Goel , Sungwon Kim , Rafael Valle , Bryan Catanzaro

It is an open challenge to obtain high quality training data, especially captions, for text-to-audio models. Although prior methods have leveraged \textit{text-only language models} to augment and improve captions, such methods have…

Computation and Language · Computer Science 2024-07-10 Zhifeng Kong , Sang-gil Lee , Deepanway Ghosal , Navonil Majumder , Ambuj Mehrish , Rafael Valle , Soujanya Poria , Bryan Catanzaro

LLM-powered code generation has the potential to revolutionize creative coding endeavors, such as live-coding, by enabling users to focus on structural motifs over syntactic details. In such domains, when prompting an LLM, users may benefit…

Multimedia · Computer Science 2025-09-25 Sam Kouteili , Hiren Madhu , George Typaldos , Mark Santolucito

Recent audio LLMs have emerged rapidly, demonstrating strong generalization across various speech tasks. However, given the inherent complexity of speech signals, these models inevitably suffer from performance degradation in specific…

Sound · Computer Science 2025-07-29 Shaowen Wang , Xinyuan Chen , Yao Xu

We introduce AudioLM, a framework for high-quality audio generation with long-term consistency. AudioLM maps the input audio to a sequence of discrete tokens and casts audio generation as a language modeling task in this representation…

Audio agents extend large audio-language models (LALMs) by decomposing audio questions into tool calls, intermediate evidence, and iterative reasoning steps. However, as LALMs become stronger, the key challenge shifts from enabling tool use…

Audio and Speech Processing · Electrical Eng. & Systems 2026-05-28 Yucheng Wang , Jing Peng , Hanqi Li , Chenghao Wang , Wenming Tu , Yu Xi , Zhaokai Sun , Kai Yu , Shuai Wang

Understanding the internal mechanisms of large audio-language models (LALMs) is crucial for interpreting their behavior and improving performance. This work presents the first in-depth analysis of how LALMs internally perceive and recognize…

Computation and Language · Computer Science 2025-08-26 Chih-Kai Yang , Neo Ho , Yi-Jyun Lee , Hung-yi Lee

The study of label noise in sound event recognition has recently gained attention with the advent of larger and noisier datasets. This work addresses the problem of missing labels, one of the big weaknesses of large audio datasets, and one…

We consider and propose a new problem of retrieving audio files relevant to multimodal design document inputs comprising both textual elements and visual imagery, e.g., birthday/greeting cards. In addition to enhancing user experience,…

Multimedia · Computer Science 2023-03-01 Prachi Singh , Srikrishna Karanam , Sumit Shekhar

AudioSet is a widely used benchmark in the audio research community and has significantly advanced various audio-related tasks. However, persistent issues with label accuracy and completeness remain critical bottlenecks that limit…

Sound · Computer Science 2025-08-25 Yulin Sun , Qisheng Xu , Yi Su , Qian Zhu , Yong Dou , Xinwang Liu , Kele Xu

Large Audio-Language Models (LALMs) have shown strong performance in speech understanding, making speech a natural interface for accessing factual information. Yet they are trained on static corpora and may encode incorrect facts. Existing…

Machine Learning · Computer Science 2026-03-17 Sung Kyun Chung , Jiaheng Dong , Qiuchi Hu , Gongping Huang , Hong Jia , Ting Dang

Retrieval-augmented generation can improve audio captioning by incorporating relevant audio-text pairs from a knowledge base. Existing methods typically rely solely on the input audio as a unimodal retrieval query. In contrast, we propose…

Sound · Computer Science 2025-06-11 Choi Changin , Lim Sungjun , Rhee Wonjong

Pre-training decoder-only language models relies on vast amounts of high-quality data, yet the availability of such data is increasingly reaching its limits. While metadata is commonly used to create and curate these datasets, its potential…

Computation and Language · Computer Science 2025-12-09 Sebastian Sztwiertnia , Felix Friedrich , Kristian Kersting , Patrick Schramowski , Björn Deiseroth