English
Related papers

Related papers: PANNs: Large-Scale Pretrained Audio Neural Network…

200 papers

Sounds carry an abundance of information about activities and events in our everyday environment, such as traffic noise, road works, music, or people talking. Recent machine learning methods, such as convolutional neural networks (CNNs),…

Sound · Computer Science 2023-05-31 Arshdeep Singh , Haohe Liu , Mark D. Plumbley

Over the past few years, audio classification task on large-scale dataset such as AudioSet has been an important research area. Several deeper Convolution-based Neural networks have shown compelling performance notably Vggish, YAMNet, and…

Sound · Computer Science 2023-05-23 Shwetank Choudhary , CR Karthik , Punuru Sri Lakshmi , Sumit Kumar

Convolutional Neural Networks (CNNs) have demonstrated exceptional performance in audio tagging tasks. However, deploying these models on resource-constrained devices like the Raspberry Pi poses challenges related to computational…

Audio pattern recognition (APR) is an important research topic and can be applied to several fields related to our lives. Therefore, accurate and efficient APR systems need to be developed as they are useful in real applications. In this…

Sound · Computer Science 2022-07-21 Sergey Verbitskiy , Vladimir Berikov , Viacheslav Vyshegorodtsev

Pattern recognition from audio signals is an active research topic encompassing audio tagging, acoustic scene classification, music classification, and other areas. Spectrogram and mel-frequency cepstral coefficients (MFCC) are among the…

Audio and Speech Processing · Electrical Eng. & Systems 2022-11-18 Md. Istiaq Ansari , Taufiq Hasan

In computer vision, convolutional neural networks (CNN) such as ConvNeXt, have been able to surpass state-of-the-art transformers, partly thanks to depthwise separable convolutions (DSC). DSC, as an approximation of the regular convolution,…

Speech enhancement is a task to improve the intelligibility and perceptual quality of degraded speech signal. Recently, neural networks based methods have been applied to speech enhancement. However, many neural network based methods…

Sound · Computer Science 2021-02-22 Qiuqiang Kong , Haohe Liu , Xingjian Du , Li Chen , Rui Xia , Yuxuan Wang

Transfer learning is commonly employed to leverage large, pre-trained models and perform fine-tuning for downstream tasks. The most prevalent pre-trained models are initially trained using ImageNet. However, their ability to generalize can…

In this paper, we examine the use of Transfer Learning using Pretrained Audio Neural Networks (PANNs), and propose an architecture that is able to better leverage the acoustic features provided by PANNs for the Automated Audio Captioning…

Computation and Language · Computer Science 2021-08-29 Andrew Koh , Fuzhao Xue , Eng Siong Chng

Audio captioning aims at using natural language to describe the content of an audio clip. Existing audio captioning systems are generally based on an encoder-decoder architecture, in which acoustic information is extracted by an audio…

Audio and Speech Processing · Electrical Eng. & Systems 2022-03-29 Xubo Liu , Xinhao Mei , Qiushi Huang , Jianyuan Sun , Jinzheng Zhao , Haohe Liu , Mark D. Plumbley , Volkan Kılıç , Wenwu Wang

Accurate multi-organ abdominal CT segmentation is essential to many clinical applications such as computer-aided intervention. As data annotation requires massive human labor from experienced radiologists, it is common that training data…

Computer Vision and Pattern Recognition · Computer Science 2019-08-22 Yuyin Zhou , Zhe Li , Song Bai , Chong Wang , Xinlei Chen , Mei Han , Elliot Fishman , Alan Yuille

Deep learning models such as CNNs and Transformers have achieved impressive performance for end-to-end audio tagging. Recent works have shown that despite stacking multiple layers, the receptive field of CNNs remains severely limited.…

Sound · Computer Science 2023-11-06 Shubhr Singh , Christian J. Steinmetz , Emmanouil Benetos , Huy Phan , Dan Stowell

Transfer learning (TL) is an increasingly popular approach to training deep learning (DL) models that leverages the knowledge gained by training a foundation model on diverse, large-scale datasets for use on downstream tasks where less…

Machine Learning · Computer Science 2024-12-06 John Fischer , Marko Orescanin , Eric Eckstrand

Transformers have set new benchmarks in audio processing tasks, leveraging self-attention mechanisms to capture complex patterns and dependencies within audio data. However, their focus on pairwise interactions limits their ability to…

Sound · Computer Science 2025-01-30 Shubhr Singh , Emmanouil Benetos , Huy Phan , Dan Stowell

In this paper, we show that ImageNet-Pretrained standard deep CNN models can be used as strong baseline networks for audio classification. Even though there is a significant difference between audio Spectrogram and standard ImageNet image…

Computer Vision and Pattern Recognition · Computer Science 2020-11-17 Kamalesh Palanisamy , Dipika Singhania , Angela Yao

The introduction of large-scale audio datasets, such as AudioSet, paved the way for Transformers to conquer the audio domain and replace CNNs as the state-of-the-art neural network architecture for many tasks. Audio Spectrogram Transformers…

Sound · Computer Science 2023-10-25 Florian Schmid , Khaled Koutini , Gerhard Widmer

The goal of speech emotion recognition (SER) is to identify the emotional aspects of speech. The SER challenge for Brazilian Portuguese speech was proposed with short snippets of Portuguese which are classified as neutral, non-neutral…

Sound · Computer Science 2022-10-27 Marcelo Matheus Gauy , Marcelo Finger

We present polynomial-augmented neural networks (PANNs), a novel machine learning architecture that combines deep neural networks (DNNs) with a polynomial approximant. PANNs combine the strengths of DNNs (flexibility and efficiency in…

Machine Learning · Computer Science 2025-02-25 Madison Cooley , Shandian Zhe , Robert M. Kirby , Varun Shankar

The success of supervised deep learning methods is largely due to their ability to learn relevant features from raw data. Deep Neural Networks (DNNs) trained on large-scale datasets are capable of capturing a diverse set of features, and…

Conventional Convolutional Neural Networks (CNNs) in the real domain have been widely used for audio classification. However, their convolution operations process multi-channel inputs independently, limiting the ability to capture…

Audio and Speech Processing · Electrical Eng. & Systems 2025-10-27 Arshdeep Singh , Vinayak Abrol , Mark D. Plumbley
‹ Prev 1 2 3 10 Next ›