Study presents a dataset and methods to handle noisy labels in sound event classification.
problem Label noise in sound event classification datasets.
method Developed a dataset with noisy labels and evaluated CNN baseline systems.
result Training with large amounts of noisy data can outperform training with carefully-labeled data.
SVM algorithm extracts digits from audio CAPTCHAs.
problem Recognizing audio CAPTCHAs from computer programs.
method Used RastaPLP features and SVM algorithm.
result Successfully extracted digits from audio CAPTCHAs.
Paper introduces a noisy-labeled audio tagging challenge.
problem Acoustic mismatch and noisy labels in audio tagging.
method Large dataset with minimal supervision, convolutional neural network baseline.
result Demonstrates effectiveness of minimal supervision in noisy conditions.
This thesis evaluates text-based vs audio-based classification of mental health interviews.
problem Classifying psychiatric illness using text-based methods.
method Design and evaluate a text classification network on mental health interviews, using belabBERT.
result Text-based classification is a strong alternative to audio-based methods.
Neural model synthesizes music with flexible timbre controls.
problem Creating audio samples with varied timbres from musical scores.
method Recurrent neural network conditioned on learned instrument embedding followed by WaveNet vocoder.
result Learned embedding space captures diverse timbres and enables interpolation for morphing.
Perceptual ad-blocking is vulnerable to attacks, creating new security risks.
problem Vulnerability of perceptual ad-blocking to attacks and new security risks.
method Analysis and creation of adversarial examples to bypass perceptual ad-blocking.
result Perceptual ad-blocking can be bypassed using adversarial examples, introducing new security risks.
Predicts which songs will be Billboard hits using Spotify data.
problem Predicting which songs will become chart-topping hits.
method Used a dataset of 1.8 million hit and non-hit songs, extracted audio features, and tested four models (random forest achieved 88% accuracy).
result Random forest model achieved 88% accuracy in predicting Billboard song success.
Web-based framework detects Parkinson's disease from speech recordings.
problem Early detection of Parkinson's disease from speech recordings.
method Collected data from 726 participants, extracted acoustic and deep learning features, trained machine learning models.
result Achieved 0.75 AUC performance in detecting Parkinson's disease.
Proposes a self-supervised method for generating spatial audio from monaural audio and video.
problem Generating spatial audio from monaural audio and video recordings is challenging and expensive.
method Uses a self-supervised network with an auxiliary classifier to classify video channels and generate spatial audio.
result The proposed method effectively generates spatial audio from monaural audio and video.
Deep audio prior uses neural networks to solve audio problems without data.
problem Challenging audio problems like source separation, editing, and synthesis.
method Randomly-initialized neural network with carefully designed audio prior.
result Superior audio results on Universal-150 benchmark dataset.
Zero-shot audio classification using class label embeddings.
problem Classifying audio without labeled data.
method Bilinear model with audio feature embeddings and class label embeddings.
result Achieved accuracy up to 39.7% for natural audio categories.
A new autoencoder speeds up audio style transfer.
problem Efficiently generating stylized audio from content audio.
method Autoencoder architecture for real-time audio style transfer.
result Single forward pass for stylized audio generation.
Method learns audio embeddings with contextualized tags.
problem Align audio and tags for cross-modal tasks.
method Audio autoencoder, word embeddings, multi-head self-attention, contrastive loss.
result Multi-head self-attention improves audio representations.
Study improves radio show segmentation using audio embeddings.
problem Automated segmentation of radio shows.
method Created audio embeddings from multi-class classification tasks on different datasets, evaluated performance against text-only baseline.
result Audio embeddings from non-speech sound event classification significantly outperformed text-only baseline by 32.3% in F1-measure.
Online audio advertising is a particular form of advertising used abundantly in online music streaming services. In these platforms, which tend to host tens of thousands of unique audio advertisements (ads), providing high quality ads ensures a better user experience and results in longer user engagement. Therefore, th…
Generative model improves audio synthesis from TF features.
problem Challenges in generating high-quality audio from TF features.
method Used a GAN to generate invertible TF features from short-time Fourier transforms.
result Generated TF features from GAN outperformed direct waveform generation.
Formula calculates MOY webs and link polynomials.
problem No specific problem stated; focuses on evaluation.
method Closed formula for exterior webs and link polynomials.
result Closed formula for evaluating MOY webs and link polynomials.
We find an invariant characterization of planar webs of maximum rank. For 4-webs, we prove that a planar 4-web is of maximum rank three if and only if it is linearizable and its curvature vanishes. This result leads to the direct web-theoretical proof of the Poincaré's theorem: a planar 4-web of maximum rank is lineari…
Adversarial attacks on spectrograms can fool audio classifiers trained on waveforms.
problem Susceptibility of audio classifiers to adversarial attacks on spectrograms.
method Applying adversarial attacks to spectrograms and reconstructing audio waveforms.
result Perturbed spectrograms can fool 2D CNNs and 1D CNNs trained on audio waveforms.
Classifies hexagonal circular 3-webs with cubic polar curves.
problem Classifying hexagonal circular 3-webs with algebraic polar curves of degree three.
method Analyzes hexagonal circular 3-webs on unit sphere with polar points on a twisted cubic.
result Completes the classification of hexagonal circular 3-webs with algebraic polar curves of degree three.
Study improves animal audio classification using data augmentation.
problem Improving automated animal audio classification accuracy.
method Exploits different data augmentation techniques for training CNNs.
result Best recognition rates on animal audio classification datasets.
MicAugment transfers audio style from few seconds of input to match target conditions.
problem Audio model robustness to diverse acquisition conditions.
method Identifies and applies transformations learned from target audio to input audio.
result MicAugment significantly improves model robustness in downstream tasks.
Detects audio adversarial examples using anomalous pattern detection.
problem Identifies adversarial audio attacks in deep neural networks.
method Applies anomalous pattern detection in activation space of audio models.
result Can detect adversarial examples with up to 0.98 AUC, no degradation on benign samples.
We construct flat 3-webs via semi-simple geometric Frobenius manifolds of dimension three and give geometric interpretation of the Chern connection of the web. These webs turned out to be biholomorphic to the characteristic webs on the solutions of the corresponding associativity equation. We show that such webs are he…
Speech enhancement (SE) aims to reduce noise in speech signals. Most SE techniques focus only on addressing audio information. In this work, inspired by multimodal learning, which utilizes data from different modalities, and the recent success of convolutional neural networks (CNNs) in SE, we propose an audio-visual de…
Speech enhancement (SE) aims to reduce noise in speech signals. Most SE techniques focus only on addressing audio information. In this work, inspired by multimodal learning, which utilizes data from different modalities, and the recent success of convolutional neural networks (CNNs) in SE, we propose an audio-visual de…
We give various results and applications using the connection (E,∇) associated with a d-web. Precisely, we exhibit fundamental invariants of the web related to the differential equation of first order which presents the web. They cast some new lights on the connection and its construction, both conceptually an…
Unified model for audio control and style transfer.
problem Explicit control and style transfer in music generation.
method Diffusion autoencoders for semantic feature extraction, disentanglement using adversarial criterion.
result Model generates audio matching timbre targets with specified structure.
Audio fingerprinting, also named as audio hashing, has been well-known as a powerful technique to perform audio identification and synchronization. It basically involves two major steps: fingerprint (voice pattern) design and matching search. While the first step concerns the derivation of a robust and compact audio si…
Transformer model estimates keywords for better audio captioning.
problem Indeterminacy in word selection for audio events/scenes.
method Transformer-based model with keyword estimation.
result Achieved state-of-the-art performance in AAC.
We investigate the linearizability problem for different classes of 4-webs in the plane. In particular, we apply a recently found in [AGL] the linearizability conditions for 4-webs in the plane to confirm that a 4-web MW (Mayrhofer's web) with equal curvature forms of its 3-subwebs and a nonconstant basic invariant is …
In the present paper we study geometric structures associated with webs of hypersurfaces. We prove that with any geodesic (n+2)-web on an n-dimensional manifold there is naturally associated a unique projective structure and, provided that one of web foliations is pointed, there is also associated a unique affine struc…
GANSynth uses GANs to efficiently synthesize high-fidelity audio.
problem Efficient and high-fidelity audio synthesis is challenging.
method Model log magnitudes and instantaneous frequencies with GANs.
result GANSynth outperforms WaveNet on automated and human evaluation metrics.
LumièreNet creates lecture videos from audio narration.
problem Creating high-quality lecture videos from audio narration.
method Modular deep-learning architecture that learns from audio to video.
result Synthesizes high-quality lecture videos from any length of audio.
Review of deep learning techniques for audio signal processing.
problem Improving audio signal processing using deep learning.
method Analysis of various deep learning models and techniques.
result Advancements in speech, music, and environmental sound processing.
This paper describes Task 2 of the DCASE 2018 Challenge, titled "General-purpose audio tagging of Freesound content with AudioSet labels". This task was hosted on the Kaggle platform as "Freesound General-Purpose Audio Tagging Challenge". The goal of the task is to build an audio tagging system that can recognize the c…
AV-CPL uses continuous pseudo-labels for AVSR combining labeled and unlabeled data.
problem Improving AVSR performance with labeled and unlabeled data.
method Semi-supervised method using continuous pseudo-labels generated by the same AVSR model.
result Significant improvements in VSR performance on LRS3 dataset.
MelNet generates high-fidelity audio with long-range structure.
problem Capturing long-range dependencies in audio waveforms.
method Generative model in frequency domain, leveraging spectrograms.
result Improves audio generation in various tasks.
HEAR benchmark evaluates audio representations for diverse tasks.
problem Developing a general-purpose audio representation for various tasks.
method Evaluated 29 models across 19 tasks using 16 datasets.
result No single audio representation performs holistically.
Study local invariants of divergence-free webs in geometry.
problem Characterize triviality of divergence-free webs.
method Introduce two local invariants: differential and geometric.
result Triviality of either invariant characterizes trivial divergence-free web-germs.
Proposes COALA method for learning audio representations aligned with tags.
problem Lack of annotated data for high-performance audio representation learning.
method Aligns latent representations of audio and tags using a contrastive loss.
result Audio embedding model captures both acoustic and semantic characteristics.
Adversarial attacks can fool copyright detection systems.
problem Vulnerability of copyright detection systems to adversarial attacks.
method Used gradient methods to create adversarial music that fooled detection systems.
result Adversarial attacks can successfully deceive industrial copyright detection tools.
This paper has been withdrawn by the authors due to the fact that the webs considered in the paper are ``Veronese-like webs'' which are different from Veronese webs.
Investigates webs related to cluster algebras and polylogarithms.
problem Understanding webs associated with cluster algebras and polylogarithms.
method Introducing AMP webs and analyzing their properties, proving results and conjectures.
result Many webs associated with polylogarithms and cluster algebras are AMP webs.
Efficient sparse GP model improves audio source separation.
problem Sparse Gaussian Process (GP) inference is computationally expensive for long audio frames.
method Used GP regression, spectral mixture kernels, and variational sparse GPs.
result Proposed method outperforms LD-PSDTF, KL-NMF, and IS-NMF.
We present a projectively invariant description of planar linear 3-webs. For a non-hexagonal 3-web, we introduce family of projective torsion-free Cartan connections, the web leaves being geodesics for each member of the family, and give a web linearization criterion. Finally, we propose an algorithm for resolving the …
Machine learning identifies species by voice in remote areas.
problem Continuous monitoring of endangered species in remote areas.
method Training machine learning models on audio data to recognize species.
result Machine learning can accurately classify and recognize various species sounds.
A new method for audio denoising using deep neural networks.
problem Improving audio quality by removing background noise.
method Combines time and time-frequency domain processing; trains a deep neural network to fit the signal.
result The method effectively disentangles clean audio from noisy signals.