English
Related papers

Related papers: Improving Audio Spectrogram Transformers for Sound…

200 papers

This paper introduces a multi-stage self-directed framework designed to address the spatial semantic segmentation of sound scene (S5) task in the DCASE 2025 Task 4 challenge. This framework integrates models focused on three distinct tasks:…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-18 Younghoo Kwon , Dongheon Lee , Dohwan Kim , Jung-Woo Choi

Self-supervised learning (SSL) has emerged as a popular approach for learning audio representations. One goal of audio self-supervised pre-training is to transfer knowledge to downstream audio tasks, generally including clip-level and…

Audio and Speech Processing · Electrical Eng. & Systems 2023-11-08 Xian Li , Nian Shao , Xiaofei Li

In this paper we present our work on Task 1 Acoustic Scene Classi- fication and Task 3 Sound Event Detection in Real Life Recordings. Among our experiments we have low-level and high-level features, classifier optimization and other…

Recently, a variety of acoustic tasks and related applications arised. For many acoustic tasks, the labeled data size may be limited. To handle this problem, we propose an unsupervised pre-training method using Transformer based encoder to…

Audio and Speech Processing · Electrical Eng. & Systems 2021-02-09 Ruixiong Zhang , Haiwei Wu , Wubo Li , Dongwei Jiang , Wei Zou , Xiangang Li

The deep learning models used for speaker verification rely heavily on large amounts of data and correct labeling. However, noisy (incorrect) labels often occur, which degrades the performance of the system. In this paper, we propose a…

Sound · Computer Science 2026-04-29 Zhihua Fang , Liang He , Hanhan Ma , Xiaochen Guo , Lin Li

This report proposes a frequency dynamic convolution (FDY) with a large kernel attention (LKA)-convolutional recurrent neural network (CRNN) with a pre-trained bidirectional encoder representation from audio transformers (BEATs)…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-13 Ji Won Kim , Sang Won Son , Yoonah Song , Hong Kook Kim , Il Hoon Song , Jeong Eun Lim

In this paper, we propose a method called Hodge and Podge for sound event detection. We demonstrate Hodge and Podge on the dataset of Detection and Classification of Acoustic Scenes and Events (DCASE) 2019 Challenge Task 4. This task aims…

Sound · Computer Science 2020-02-17 Ziqiang Shi , Liu Liu , Huibin Lin , Rujie Liu

While deep learning has been incredibly successful in modeling tasks with large, carefully curated labeled datasets, its application to problems with limited labeled data remains a challenge. The aim of the present work is to improve the…

Audio and Speech Processing · Electrical Eng. & Systems 2019-10-29 Tyler Lee , Ting Gong , Suchismita Padhy , Andrew Rouditchenko , Anthony Ndirango

The massive growth of self-supervised learning (SSL) has been witnessed in language, vision, speech, and audio domains over the past few years. While discrete label prediction is widely adopted for other modalities, the state-of-the-art…

Audio and Speech Processing · Electrical Eng. & Systems 2022-12-20 Sanyuan Chen , Yu Wu , Chengyi Wang , Shujie Liu , Daniel Tompkins , Zhuo Chen , Furu Wei

In this technical report, we present a joint effort of four groups, namely GT, USTC, Tencent, and UKE, to tackle Task 1 - Acoustic Scene Classification (ASC) in the DCASE 2020 Challenge. Task 1 comprises two different sub-tasks: (i) Task 1a…

This study (The work was accomplished during the internship in Tencent AI lab) addresses semi-supervised acoustic modeling, i.e. attaining high-level representations from unsupervised audio data and fine-tuning the parameters of pre-trained…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-14 Lu Liu , Yiheng Huang

Audio Event Detection (AED) aims to recognize sounds within audio and video recordings. AED employs machine learning algorithms commonly trained and tested on annotated datasets. However, available datasets are limited in number of samples…

Acoustic scene classification (ASC) predominantly relies on supervised approaches. However, acquiring labeled data for training ASC models is often costly and time-consuming. Recently, self-supervised learning (SSL) has emerged as a…

Sound · Computer Science 2024-08-28 Yiqiang Cai , Shengchen Li , Xi Shao

Weakly Labelled learning has garnered lot of attention in recent years due to its potential to scale Sound Event Detection (SED) and is formulated as Multiple Instance Learning (MIL) problem. This paper proposes a Multi-Task Learning (MTL)…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-02 Soham Deshmukh , Bhiksha Raj , Rita Singh

Environmental sound analysis is currently getting more and more attentions. In the domain, acoustic scene classification and acoustic event classification are two closely related tasks. In this letter, a two-stage method is proposed for the…

Sound · Computer Science 2021-03-31 Weiping Zheng , Dacan Jiang , Gansen Zhao

In this paper, we present a method called HODGEPODGE\footnotemark[1] for large-scale detection of sound events using weakly labeled, synthetic, and unlabeled data proposed in the Detection and Classification of Acoustic Scenes and Events…

Sound · Computer Science 2019-07-18 Ziqiang Shi , Liu Liu , Huibin Lin , Rujie Liu , Anyan Shi

Sound event detection (SED) is typically posed as a supervised learning problem requiring training data with strong temporal labels of sound events. However, the production of datasets with strong labels normally requires unaffordable labor…

Sound · Computer Science 2018-11-02 Dezhi Wang , Lilun Zhang , Changchun Bao , Kele Xu , Boqing Zhu , Qiuqiang Kong

Deep learning models have demonstrated remarkable success in multi-organ segmentation but typically require large-scale datasets with all organs of interest annotated. However, medical image datasets are often low in sample size and only…

Computer Vision and Pattern Recognition · Computer Science 2023-11-03 Han Liu , Zhoubing Xu , Riqiang Gao , Hao Li , Jianing Wang , Guillaume Chabin , Ipek Oguz , Sasa Grbic

Sound event detection (SED) is the task of tagging the absence or presence of audio events and their corresponding interval within a given audio clip. While SED can be done using supervised machine learning, where training data is fully…

Sound · Computer Science 2021-02-08 Heinrich Dinkel , Mengyue Wu , Kai Yu

We present the task description of the Detection and Classification of Acoustic Scenes and Events (DCASE) 2023 Challenge Task 2: ``First-shot unsupervised anomalous sound detection (ASD) for machine condition monitoring''. The main goal is…