Search Results for author:
Found 17 papers, 14 papers with code
Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio Models
Audio Spectrogram Transformers are excellent at exploiting large datasets, creating powerful pre-trained models that surpass CNNs when fine-tuned on downstream tasks.
Ranked #1 on
Instrument Recognition
on OpenMIC-2018
(using extra training data)
Advancing Natural-Language Based Audio Retrieval with PaSST and Large Audio-Caption Data Sets
This work presents a text-to-audio-retrieval system based on pre-trained text and spectrogram transformers.
Domain Information Control at Inference Time for Acoustic Scene Classification
In the Acoustic Scene Classification task (ASC), domain shift is mainly caused by different recording devices.
Device-Robust Acoustic Scene Classification via Impulse Response Augmentation
However, we also show that DIR augmentation and Freq-MixStyle are complementary, achieving a new state-of-the-art performance on signals recorded by devices unseen during training.
Learning General Audio Representations with Large-Scale Training of Patchout Audio Transformers
Furthermore, we will show that transformers trained on Audioset can be extremely effective representation extractors for a wide range of downstream tasks.
Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation
We provide models of different complexity levels, scaling from low-complexity models up to a new state-of-the-art performance of . 483 mAP on AudioSet.
Ranked #2 on
Audio Tagging
on AudioSet
(using extra training data)
Efficient Training of Audio Transformers with Patchout
However, one of the main shortcomings of transformer models, compared to the well-established CNNs, is the computational complexity.
Ranked #3 on
Audio Classification
on FSD50K
(using extra training data)
Over-Parameterization and Generalization in Audio Classification
Convolutional Neural Networks (CNNs) have been dominating classification tasks in various domains, such as machine vision, machine listening, and natural language processing.
Receptive Field Regularization Techniques for Audio Classification and Tagging with Deep Convolutional Neural Networks
As state-of-the-art CNN architectures-in computer vision and other domains-tend to go deeper in terms of number of layers, their RF size increases and therefore they degrade in performance in several audio classification and tagging tasks.
Low-Complexity Models for Acoustic Scene Classification Based on Receptive Field Regularization and Frequency Damping
Deep Neural Networks are known to be very demanding in terms of computing and memory requirements.
Receptive-Field Regularized CNNs for Music Classification and Tagging
However, the MIR field is still dominated by the classical VGG-based CNN architecture variants, often in combination with more complex modules such as attention, and/or techniques such as pre-training on large datasets.
On Data Augmentation and Adversarial Risk: An Empirical Analysis
Data augmentation techniques have become standard practice in deep learning, as it has been shown to greatly improve the generalisation abilities of models.
Emotion and Theme Recognition in Music with Frequency-Aware RF-Regularized CNNs
We present CP-JKU submission to MediaEval 2019; a Receptive Field-(RF)-regularized and Frequency-Aware CNN approach for tagging music with emotion/mood labels.
Receptive-field-regularized CNN variants for acoustic scene classification
One side effect of restricting the RF of CNNs is that more frequency information is lost.
Exploiting Parallel Audio Recordings to Enforce Device Invariance in CNN-based Acoustic Scene Classification
Distribution mismatches between the data seen at training and at application time remain a major challenge in all application areas of machine learning.
The Receptive Field as a Regularizer in Deep Convolutional Neural Networks for Acoustic Scene Classification
To this end, we analyse the receptive field (RF) of these CNNs and demonstrate the importance of the RF to the generalization capability of the models.
Deep SNP: An End-to-end Deep Neural Network with Attention-based Localization for Break-point Detection in SNP Array Genomic data
We show, that Deep SNP is capable of successfully predicting the presence or absence of a breakpoint in large genomic windows and outperforms state-of-the-art neural network models.
