English
Related papers

Related papers: From Coarse to Fine: Efficient Training for Audio …

200 papers

One solution to automatic speech recognition (ASR) of overlapping speakers is to separate speech and then perform ASR on the separated signals. Commonly, the separator produces artefacts which often degrade ASR performance. Addressing this…

One key step in audio signal processing is to transform the raw signal into representations that are efficient for encoding the original information. Traditionally, people transform the audio into spectral representations, as a function of…

Sound · Computer Science 2016-11-30 Shuhui Qu , Juncheng Li , Wei Dai , Samarjit Das

Standard fine-tuning of pre-trained audio models couples representation learning with classifier training, which can obscure the true quality of the learned representations. In this work, we advocate for a disentangled two-stage framework…

Sound · Computer Science 2025-09-23 Yang Wang , Qibin Liang , Chenghao Xiao , Yizhi Li , Noura Al Moubayed , Chenghua Lin

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

The rapid advancement of artificial intelligence (AI) has enabled sophisticated audio generation and voice cloning technologies, posing significant security risks for applications reliant on voice authentication. While existing datasets and…

Sound · Computer Science 2025-05-22 Kunyang Huang , Bin Hu

Transformers (Vaswani et al., 2017) have brought a remarkable improvement in the performance of neural machine translation (NMT) systems but they could be surprisingly vulnerable to noise. In this work, we try to investigate how noise…

Computation and Language · Computer Science 2021-09-13 Peyman Passban , Puneeth S. M. Saladi , Qun Liu

Unmanned aerial vehicle (UAV) usage is expected to surge in the coming decade, raising the need for heightened security measures to prevent airspace violations and security threats. This study investigates deep learning approaches to UAV…

Sound · Computer Science 2025-07-25 Andrew P. Berg , Qian Zhang , Mia Y. Wang

Recently, attention-based transformers have become a de facto standard in many deep learning applications including natural language processing, computer vision, signal processing, etc.. In this paper, we propose a transformer-based…

Sound · Computer Science 2024-09-04 Tathagata Bandyopadhyay

Adversarial training has been considered an imperative component for safely deploying neural network-based applications to the real world. To achieve stronger robustness, existing methods primarily focus on how to generate strong attacks by…

Machine Learning · Computer Science 2023-09-01 Yeachan Kim , Seongyeon Kim , Ihyeok Seo , Bonggun Shin

A transformer-based deep learning approach is presented that enables the diagnosis of fault cases in optical fiber amplifiers using condition-based monitoring time series data. The model, Inverse Triple-Aspect Self-Attention Transformer…

Signal Processing · Electrical Eng. & Systems 2025-09-05 Dominic Schneider , Lutz Rapp , Christoph Ament

With the proliferation of video platforms on the internet, recording musical performances by mobile devices has become commonplace. However, these recordings often suffer from degradation such as noise and reverberation, which negatively…

Sound · Computer Science 2023-08-25 Yunkee Chae , Junghyun Koo , Sungho Lee , Kyogu Lee

Machine learning approaches to modelling analog audio effects have seen intensive investigation in recent years, particularly in the context of non-linear time-invariant effects such as guitar amplifiers. For modulation effects such as…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-05 Alistair Carson , Cassia Valentini-Botinhao , Simon King , Stefan Bilbao

Disentangling and recovering physical attributes, such as shape and material, from a few waveform examples is a challenging inverse problem in audio signal processing, with numerous applications in musical acoustics as well as structural…

Sound · Computer Science 2020-07-21 Han Han , Vincent Lostanlen

Recent studies show that pretrained vision models can boost performance in audio downstream tasks. To enhance the performance further, an additional pretraining stage with large scale audio data is typically required to infuse audio…

Sound · Computer Science 2024-12-10 Juan Yeo , Jinkwan Jang , Kyubyung Chae , Seongkyu Mun , Taesup Kim

Many algorithms have been developed to solve the inverse problem of coded aperture snapshot spectral imaging (CASSI), i.e., recovering the 3D hyperspectral images (HSIs) from a 2D compressive measurement. In recent years, learning-based…

Computer Vision and Pattern Recognition · Computer Science 2022-07-12 Yuanhao Cai , Jing Lin , Xiaowan Hu , Haoqian Wang , Xin Yuan , Yulun Zhang , Radu Timofte , Luc Van Gool

We propose a pre-training pipeline for audio spectrogram transformers for frame-level sound event detection tasks. On top of common pre-training steps, we add a meticulously designed training routine on AudioSet frame-level annotations.…

Audio and Speech Processing · Electrical Eng. & Systems 2024-12-02 Florian Schmid , Tobias Morocutti , Francesco Foscarin , Jan Schlüter , Paul Primus , Gerhard Widmer

Recent advances in the field of abstractive summarization leverage pre-trained language models rather than train a model from scratch. However, such models are sluggish to train and accompanied by a massive overhead. Researchers have…

Computation and Language · Computer Science 2022-09-01 Zheng Zhao , Pinzhen Chen

In audio processing applications, phase retrieval (PR) is often performed from the magnitude of short-time Fourier transform (STFT) coefficients. Although PR performance has been observed to depend on the considered STFT parameters and…

Signal Processing · Electrical Eng. & Systems 2021-06-10 Andrés Marafioti , Nicki Holighaus , Piotr Majdak

Environmental Sound Classification (ESC) is a rapidly evolving field that recently demonstrated the advantages of application of visual domain techniques to the audio-related tasks. Previous studies indicate that the domain-specific…

Sound · Computer Science 2021-04-26 Andrey Guzhov , Federico Raue , Jörn Hees , Andreas Dengel

Low-resource accented speech recognition is one of the important challenges faced by current ASR technology in practical applications. In this study, we propose a Conformer-based architecture, called Aformer, to leverage both the acoustic…

Sound · Computer Science 2023-06-21 Xuefei Wang , Yanhua Long , Yijie Li , Haoran Wei