English
Related papers

Related papers: The ICME 2025 Audio Encoder Capability Challenge

200 papers

The task of speaker change detection (SCD), which detects points where speakers change in an input, is essential for several applications. Several studies solved the SCD task using audio inputs only and have shown limited performance.…

This paper describes our submitted systems to the 2022 ADD challenge withing the tracks 1 and 2. Our approach is based on the combination of a pre-trained wav2vec2 feature extractor and a downstream classifier to detect spoofed audio. This…

Audio and Speech Processing · Electrical Eng. & Systems 2022-03-04 Juan M. Martín-Doñas , Aitor Álvarez

Long (> 200 ms) audio inpainting, to recover a long missing part in an audio segment, could be widely applied to audio editing tasks and transmission loss recovery. It is a very challenging problem due to the high dimensional, complex and…

Sound · Computer Science 2019-11-18 Ya-Liang Chang , Kuan-Ying Lee , Po-Yu Wu , Hung-yi Lee , Winston Hsu

This paper introduces FastVC, an end-to-end model for fast Voice Conversion (VC). The proposed model can convert speech of arbitrary length from multiple source speakers to multiple target speakers. FastVC is based on a conditional…

Audio and Speech Processing · Electrical Eng. & Systems 2021-05-07 Oriol Barbany Mayor , Milos Cernak

This work describes our group's submission to the PROCESS Challenge 2024, with the goal of assessing cognitive decline through spontaneous speech, using three guided clinical tasks. This joint effort followed a holistic approach,…

Recently, instruction-following audio-language models have received broad attention for audio interaction with humans. However, the absence of pre-trained audio models capable of handling diverse audio types and tasks has hindered progress…

Audio and Speech Processing · Electrical Eng. & Systems 2023-12-22 Yunfei Chu , Jin Xu , Xiaohuan Zhou , Qian Yang , Shiliang Zhang , Zhijie Yan , Chang Zhou , Jingren Zhou

Our study investigates an approach for understanding musical performances through the lens of audio encoding models, focusing on the domain of solo Western classical piano music. Compared to composition-level attribute understanding such as…

Audio and Speech Processing · Electrical Eng. & Systems 2024-07-22 Huan Zhang , Jinhua Liang , Simon Dixon

Continuously learning new classes without catastrophic forgetting is a challenging problem for on-device environmental sound classification given the restrictions on computation resources (e.g., model size, running memory). To address this…

Sound · Computer Science 2022-07-19 Yang Xiao , Xubo Liu , James King , Arshdeep Singh , Eng Siong Chng , Mark D. Plumbley , Wenwu Wang

A universal audio representation should capture fine-grained speech cues and high-level semantics for environmental sounds and music in a single encoder. Existing encoders often excel in one domain but degrade in others. We propose…

Sound · Computer Science 2026-03-10 Yuxuan Chen , Peize He , Haoyuan Yu , Junzi Zhang

In industry, machine anomalous sound detection (ASD) is in great demand. However, collecting enough abnormal samples is difficult due to the high cost, which boosts the rapid development of unsupervised ASD algorithms. Autoencoder (AE)…

Sound · Computer Science 2023-11-16 Yifan Zhou , Dongxing Xu , Haoran Wei , Yanhua Long

Audio-Visual Segmentation (AVS) is a challenging task, which aims to segment sounding objects in video frames by exploring audio signals. Generally AVS faces two key challenges: (1) Audio signals inherently exhibit a high degree of…

Sound · Computer Science 2023-12-27 Yuhang Ling , Yuxi Li , Zhenye Gan , Jiangning Zhang , Mingmin Chi , Yabiao Wang

Generating audio captions is a new research area that combines audio and natural language processing to create meaningful textual descriptions for audio clips. To address this problem, previous studies mostly use the encoder-decoder based…

Sound · Computer Science 2021-05-14 Ayşegül Özkaya Eren , Mustafa Sert

This paper reviews the AIM 2019 challenge on real world super-resolution. It focuses on the participating methods and final results. The challenge addresses the real world setting, where paired true high and low-resolution images are…

The primary goal of the L3DAS23 Signal Processing Grand Challenge at ICASSP 2023 is to promote and support collaborative research on machine learning for 3D audio signal processing, with a specific emphasis on 3D speech enhancement and 3D…

Audio and Speech Processing · Electrical Eng. & Systems 2024-02-15 Christian Marinoni , Riccardo Fosco Gramaccioni , Changan Chen , Aurelio Uncini , Danilo Comminiello

We explore self-supervised models that can be potentially deployed on mobile devices to learn general purpose audio representations. Specifically, we propose methods that exploit the temporal context in the spectrogram domain. One method…

Audio and Speech Processing · Electrical Eng. & Systems 2019-05-29 Marco Tagliasacchi , Beat Gfeller , Félix de Chaumont Quitry , Dominik Roblek

We introduce ITTO, a challenging new benchmark suite for evaluating and diagnosing the capabilities and limitations of point tracking methods. Our videos are sourced from existing datasets and egocentric real-world recordings, with…

Computer Vision and Pattern Recognition · Computer Science 2025-10-23 Ilona Demler , Saumya Chauhan , Georgia Gkioxari

In this paper, we describe our contribution to Task 2 of the DCASE 2018 Audio Challenge. While it has become ubiquitous to utilize an ensemble of machine learning methods for classification tasks to obtain better predictive performance, the…

Sound · Computer Science 2018-11-28 Marcel Lederle , Benjamin Wilhelm

Audio-Language models jointly learn multimodal text and audio representations that enable Zero-Shot inference. Models rely on the encoders to create powerful representations of the input and generalize to multiple tasks ranging from sounds,…

Sound · Computer Science 2024-02-08 Benjamin Elizalde , Soham Deshmukh , Huaming Wang

The speech field is evolving to solve more challenging scenarios, such as multi-channel recordings with multiple simultaneous talkers. Given the many types of microphone setups out there, we present the UniX-Encoder. It's a universal…

Audio and Speech Processing · Electrical Eng. & Systems 2023-10-26 Zili Huang , Yiwen Shao , Shi-Xiong Zhang , Dong Yu

Fr\'echet Audio Distance (FAD) is the de facto standard for evaluating text-to-audio generation, yet its scores depend on the underlying encoder's embedding space. An encoder's training task dictates which acoustic features are preserved or…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-02 Wonwoo Jeong