English
Related papers

Related papers: Weakly-supervised Automated Audio Captioning via t…

200 papers

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…

Audio and Speech Processing · Electrical Eng. & Systems 2022-02-09 Vin Sachidananda , Shao-Yen Tseng , Erik Marchi , Sachin Kajarekar , Panayiotis Georgiou

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

Contrastive language--audio pretraining (CLAP) has achieved remarkable success as an audio--text embedding framework, but existing approaches are limited to monaural or single-source conditions and cannot fully capture spatial information.…

Most existing masked audio modeling (MAM) methods learn audio representations by masking and reconstructing local spectrogram patches. However, the reconstruction loss mainly accounts for the signal-level quality of the reconstructed…

Sound · Computer Science 2024-01-30 Yifei Xin , Xiulian Peng , Yan Lu

Recently, there has been an increasing focus on audio-text cross-modal learning. However, most of the existing audio-text datasets contain only simple descriptions of sound events. Compared with classification labels, the advantages of such…

Sound · Computer Science 2024-03-08 Xuenan Xu , Xiaohang Xu , Zeyu Xie , Pingyue Zhang , Mengyue Wu , Kai Yu

Automated Audio Captioning is a cross-modal task, generating natural language descriptions to summarize the audio clips' sound events. However, grounding the actual sound events in the given audio based on its corresponding caption has not…

Sound · Computer Science 2021-02-24 Xuenan Xu , Heinrich Dinkel , Mengyue Wu , Kai Yu

In this paper, we propose a multi-level attention model to solve the weakly labelled audio classification problem. The objective of audio classification is to predict the presence or absence of audio events in an audio clip. Recently,…

Audio and Speech Processing · Electrical Eng. & Systems 2018-03-08 Changsong Yu , Karim Said Barsim , Qiuqiang Kong , Bin Yang

This project involved participation in the DCASE 2022 Competition (Task 6) which had two subtasks: (1) Automated Audio Captioning and (2) Language-Based Audio Retrieval. The first subtask involved the generation of a textual description for…

Sound · Computer Science 2023-05-16 Clive Gomes , Hyejin Park , Patrick Kollman , Yi Song , Iffanice Houndayi , Ankit Shah

Recent advances in using language models to obtain cross-modal audio-text representations have overcome the limitations of conventional training approaches that use predefined labels. This has allowed the community to make progress in tasks…

Audio-text retrieval (ATR), which retrieves a relevant caption given an audio clip (A2T) and vice versa (T2A), has recently attracted much research attention. Existing methods typically aggregate information from each modality into a single…

Sound · Computer Science 2024-03-18 Qian Wang , Jia-Chen Gu , Zhen-Hua Ling

Humans do not acquire perceptual abilities in the way we train machines. While machine learning algorithms typically operate on large collections of randomly-chosen, explicitly-labeled examples, human acquisition relies more heavily on…

Since acquiring pixel-wise annotations for training convolutional neural networks for semantic image segmentation is time-consuming, weakly supervised approaches that only require class tags have been proposed. In this work, we propose…

Computer Vision and Pattern Recognition · Computer Science 2019-05-17 Johann Sawatzky , Debayan Banerjee , Juergen Gall

Automated audio captioning aims to use natural language to describe the content of audio data. This paper presents an audio captioning system with an encoder-decoder architecture, where the decoder predicts words based on audio features…

Audio and Speech Processing · Electrical Eng. & Systems 2021-08-06 Xinhao Mei , Qiushi Huang , Xubo Liu , Gengyun Chen , Jingqian Wu , Yusong Wu , Jinzheng Zhao , Shengchen Li , Tom Ko , H Lilian Tang , Xi Shao , Mark D. Plumbley , Wenwu Wang

Audio-text retrieval based on natural language descriptions is a challenging task. It involves learning cross-modality alignments between long sequences under inadequate data conditions. In this work, we investigate several audio features…

Sound · Computer Science 2022-03-30 Siyu Lou , Xuenan Xu , Mengyue Wu , Kai Yu

Image captioning, a fundamental task in vision-language understanding, seeks to generate accurate natural language descriptions for provided images. Current image captioning approaches heavily rely on high-quality image-caption pairs, which…

Computer Vision and Pattern Recognition · Computer Science 2023-11-03 Chuanyang Jin

Audio captioning aims at generating natural language descriptions for audio clips automatically. Existing audio captioning models have shown promising improvement in recent years. However, these models are mostly trained via maximum…

Audio and Speech Processing · Electrical Eng. & Systems 2022-03-30 Xinhao Mei , Xubo Liu , Jianyuan Sun , Mark D. Plumbley , Wenwu Wang

Supervised image captioning approaches have made great progress, but it is challenging to collect high-quality human-annotated image-text data. Recently, large-scale vision and language models (e.g., CLIP) and large-scale generative…

Computer Vision and Pattern Recognition · Computer Science 2024-03-29 Yiyu Wang , Hao Luo , Jungang Xu , Yingfei Sun , Fan Wang

Automatic Audio Captioning (AAC) is the task that aims to describe an audio signal using natural language. AAC systems take as input an audio signal and output a free-form text sentence, called a caption. Evaluating such systems is not…

Sound · Computer Science 2022-11-17 Etienne Labbé , Thomas Pellegrini , Julien Pinquier

State-of-the-art audio classification often employs a zero-shot approach, which involves comparing audio embeddings with embeddings from text describing the respective audio class. These embeddings are usually generated by neural networks…

Sound · Computer Science 2025-07-29 James Taylor , Wolfgang Mack

We consider the task of image-captioning using only the CLIP model and additional text data at training time, and no additional captioned images. Our approach relies on the fact that CLIP is trained to make visual and textual embeddings…

Computer Vision and Pattern Recognition · Computer Science 2023-10-13 David Nukrai , Ron Mokady , Amir Globerson