English
Related papers

Related papers: M2D-CLAP: Exploring General-purpose Audio-Language…

200 papers

In recent years, datasets of paired audio and captions have enabled remarkable success in automatically generating descriptions for audio clips, namely Automated Audio Captioning (AAC). However, it is labor-intensive and time-consuming to…

Sound · Computer Science 2023-09-22 Theodoros Kouzelis , Vassilis Katsouros

Contrastively pretrained audio-language models (e.g., CLAP) excel at clip-level understanding but struggle with frame-level tasks. Existing extensions fail to exploit the varying granularity of real-world audio-text data, where massive…

Sound · Computer Science 2026-04-02 Xiquan Li , Xuenan Xu , Ziyang Ma , Wenxi Chen , Haolin He , Qiuqiang Kong , Xie Chen

Joint embedding spaces have significantly advanced music understanding and generation by linking text and audio through multimodal contrastive learning. However, these approaches face large memory requirement limitations due to relying on…

Sound · Computer Science 2025-06-24 Julien Guinot , Alain Riou , Elio Quinton , György Fazekas

Binary code representation learning has shown significant performance in binary analysis tasks. But existing solutions often have poor transferability, particularly in few-shot and zero-shot scenarios where few or no training samples are…

Software Engineering · Computer Science 2024-02-28 Hao Wang , Zeyu Gao , Chao Zhang , Zihan Sha , Mingyang Sun , Yuchen Zhou , Wenyu Zhu , Wenju Sun , Han Qiu , Xi Xiao

Unsupervised 3D representation learning reduces the burden of labeling multimodal 3D data for fusion perception tasks. Among different pre-training paradigms, differentiable-rendering-based methods have shown most promise. However, existing…

Computer Vision and Pattern Recognition · Computer Science 2026-03-02 Runjian Chen , Hang Zhang , Avinash Ravichandran , Hyoungseob Park , Wenqi Shao , Alex Wong , Ping Luo

Contrastive vision-language models, such as CLIP, have garnered considerable attention for various downstream tasks, mainly due to the remarkable ability of the learned features for generalization. However, the features they learned often…

Computer Vision and Pattern Recognition · Computer Science 2025-04-24 Yichao Cai , Yuhang Liu , Zhen Zhang , Javen Qinfeng Shi

Contrastive Language-Audio Pretraining (CLAP) models are widely used for audio understanding and support modality-agnostic condition swapping in many zero-shot applications. However, their performance is heavily affected by the modality gap…

Sound · Computer Science 2026-05-29 Yonggang Zhu , Liting Gao , Aidong Men , Wenwu Wang

Contrastive cross-modality pretraining has recently exhibited impressive success in diverse fields, whereas there is limited research on their merits in speech emotion recognition (SER). In this paper, we propose GEmo-CLAP, a kind of…

Computation and Language · Computer Science 2023-12-05 Yu Pan , Yanni Hu , Yuguang Yang , Wen Fei , Jixun Yao , Heng Lu , Lei Ma , Jianjun Zhao

Contrastive Language-Audio Pretraining (CLAP) models have demonstrated unprecedented performance in various acoustic signal recognition tasks. Fiber-optic-based acoustic recognition is one of the most important downstream tasks and plays a…

Audio and Speech Processing · Electrical Eng. & Systems 2025-01-20 Jingchen Sun , Shaobo Han , Wataru Kohno , Changyou Chen

Contrastive cross-modal models such as CLIP and CLAP aid various vision-language (VL) and audio-language (AL) tasks. However, there has been limited investigation of and improvement in their language encoder, which is the central component…

Computation and Language · Computer Science 2023-10-23 Mengjie Zhao , Junya Ono , Zhi Zhong , Chieh-Hsin Lai , Yuhta Takida , Naoki Murata , Wei-Hsiang Liao , Takashi Shibuya , Hiromi Wakaki , Yuki Mitsufuji

Learning to associate audio with textual descriptions is valuable for a range of tasks, including pretraining, zero-shot classification, audio retrieval, audio captioning, and text-conditioned audio generation. Existing contrastive…

Audio and Speech Processing · Electrical Eng. & Systems 2025-05-13 Paul Primus , Florian Schmid , Gerhard Widmer

Universal sound separation (USS) aims to extract arbitrary types of sounds from real-world recordings. This can be achieved by language-queried target sound extraction (TSE), which typically consists of two components: a query network that…

Audio and Speech Processing · Electrical Eng. & Systems 2025-03-24 Hao Ma , Zhiyuan Peng , Xu Li , Mingjie Shao , Xixin Wu , Ju Liu

Music recommender systems frequently utilize network-based models to capture relationships between music pieces, artists, and users. Although these relationships provide valuable insights for predictions, new music pieces or artists often…

Sound · Computer Science 2024-09-16 Florian Grötschla , Luca Strässle , Luca A. Lanzendörfer , Roger Wattenhofer

For fine-grained generation and recognition tasks such as minimally-supervised text-to-speech (TTS), voice conversion (VC), and automatic speech recognition (ASR), the intermediate representations extracted from speech should serve as a…

Audio and Speech Processing · Electrical Eng. & Systems 2023-12-19 Chunyu Qiang , Hao Li , Yixin Tian , Ruibo Fu , Tao Wang , Longbiao Wang , Jianwu Dang

Contrastive language-image pre-training (CLIP) is a powerful vision-language model that has shown great benefits for various tasks. However, we have identified some issues with its explainability, which undermine its credibility and limit…

Computer Vision and Pattern Recognition · Computer Science 2024-09-17 Yi Li , Hualiang Wang , Yiqun Duan , Jiheng Zhang , Xiaomeng Li

Abusive speech detection is becoming increasingly important as social media shifts towards voice-based interaction, particularly in multilingual and low-resource settings. Most current systems rely on automatic speech recognition (ASR)…

Sound · Computer Science 2026-04-13 Aditya Narayan Sankaran , Reza Farahbakhsh , Noel Crespi

Recent speaker verification studies have achieved notable success by leveraging layer-wise output from pre-trained Transformer models. However, few have explored the advancements in aggregating these multi-level features beyond the static…

Sound · Computer Science 2025-12-30 Jin Sob Kim , Hyun Joon Park , Wooseok Shin , Sung Won Han

The integration of Federated Learning (FL) and Self-supervised Learning (SSL) offers a unique and synergetic combination to exploit the audio data for general-purpose audio understanding, without compromising user data privacy. However,…

Sound · Computer Science 2024-02-07 Yasar Abbas Ur Rehman , Kin Wai Lau , Yuyang Xie , Lan Ma , Jiajun Shen

Self-supervised learning (SSL) approaches, such as contrastive and generative methods, have advanced environmental sound representation learning using unlabeled data. However, how these approaches can complement each other within a unified…

Sound · Computer Science 2025-10-29 Sivan Ding , Julia Wilkins , Magdalena Fuentes , Juan Pablo Bello

While automated audio captioning (AAC) has made notable progress, traditional fully supervised AAC models still face two critical challenges: the need for expensive audio-text pair data for training and performance degradation when…

Sound · Computer Science 2025-01-07 Xiquan Li , Wenxi Chen , Ziyang Ma , Xuenan Xu , Yuzhe Liang , Zhisheng Zheng , Qiuqiang Kong , Xie Chen