A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Self-supervised attention model improves weakly labeled audio event classification.
Study improves radio show segmentation using audio embeddings.
Improved audio event recognition using audiovisual transformers.
Transformer model estimates keywords for better audio captioning.
We introduce a new learned descriptor for audio signals which is efficient for event representation. The entries of the descriptor are produced by evaluating a set of regressors on the input signal. The regressors are class-specific and trained using the random regression forests framework. Given an input signal, each …
We propose a multi-label multi-task framework based on a convolutional recurrent neural network to unify detection of isolated and overlapping audio events. The framework leverages the power of convolutional recurrent neural network architectures; convolutional layers learn effective features over which higher recurren…
FSD50K provides an open dataset of over 51k audio clips for sound event recognition.
Meta-learning improves few-shot acoustic event detection.
Proposes COALA method for learning audio representations aligned with tags.
Even in the absence of any explicit semantic annotation, vast collections of audio recordings provide valuable information for learning the categorical structure of sounds. We consider several class-agnostic semantic constraints that apply to unlabeled nonspeech audio: (i) noise and translations in time do not change t…
As sound event classification moves towards larger datasets, issues of label noise become inevitable. Web sites can supply large volumes of user-contributed audio and metadata, but inferring labels from this metadata introduces errors due to unreliable inputs, and limitations in the mapping. There is, however, little r…
Convolutional Neural Networks (CNNs) have proven very effective in image classification and show promise for audio. We use various CNN architectures to classify the soundtracks of a dataset of 70M training videos (5.24 million hours) with 30,871 video-level labels. We examine fully connected Deep Neural Networks (DNNs)…
As part of the 2016 public evaluation challenge on Detection and Classification of Acoustic Scenes and Events (DCASE 2016), the second task focused on evaluating sound event detection systems using synthetic mixtures of office sounds. This task, which follows the `Event Detection - Office Synthetic' task of DCASE 2013,…
System tackles indeterminacies in automated audio captioning.
Classifiers and beamforming algorithms improved audio surveillance detection accuracy.
Improved acoustic scene classification with factorized CNN.
Smart city surveillance benefits from sound event recognition.
Crowd-sourced mosquito audio dataset for malaria research.
We propose a method to perform audio event detection under the common constraint that only limited training data are available. In training a deep learning system to perform audio event detection, two practical problems arise. Firstly, most datasets are "weakly labelled" having only a list of events present in each rec…
This paper proposes a zero-shot learning approach for audio classification based on the textual information about class labels without any audio samples from target classes. We propose an audio classification system built on the bilinear model, which takes audio feature embeddings and semantic class label embeddings as…
Simple methods boost sound event classifier accuracy by 2.5%.
Study improves animal audio classification using data augmentation.
New method separates sounds with weak labels in noisy environments.
Paper improves sound event detection using semi-supervised learning.
This thesis evaluates text-based vs audio-based classification of mental health interviews.
Classification of audio samples is an important part of many auditory systems. Deep learning models based on the Convolutional and the Recurrent layers are state-of-the-art in many such tasks. In this paper, we approach audio classification tasks using capsule networks trained by recently proposed dynamic routing-by-ag…
We propose a simple but efficient method termed Guided Learning for weakly-labeled semi-supervised sound event detection (SED). There are two sub-targets implied in weakly-labeled SED: audio tagging and boundary detection. Instead of designing a single model by considering a trade-off between the two sub-targets, we de…
CNNs improve generalization to unseen audio devices with increased width, not depth.
Reduces sound event localization error by 2.6x with hybrid parametric-deep learning.
Improved audio classification with limited labels using multitask and self-supervised learning.
New neural network improves audio classification accuracy.
Generating musical audio directly with neural networks is notoriously difficult because it requires coherently modeling structure at many different timescales. Fortunately, most music is also highly structured and can be represented as discrete note events played on musical instruments. Herein, we show that by using no…
Previous attempts at music artist classification use frame level audio features which summarize frequency content within short intervals of time. Comparatively, more recent music information retrieval tasks take advantage of temporal structure in audio spectrograms using deep convolutional and recurrent models. This pa…
Level assessment for foreign language students is necessary for putting them in the right level group, furthermore, interviewing students is a very time-consuming task, so we propose to automate the evaluation of speaker fluency level by implementing machine learning techniques. This work presents an audio processing s…
Graph neural networks improve music genre classification on audio datasets.
In training a deep learning system to perform audio transcription, two practical problems may arise. Firstly, most datasets are weakly labelled, having only a list of events present in each recording without any temporal information for training. Secondly, deep neural networks need a very large amount of labelled train…
A multi-head attention network improves ASC by recognizing overlapping sound patterns.
Paper presents an audiovisual model to recognize sounds from weakly labeled video data.
Method learns audio embeddings with contextualized tags.
Self-paced ensemble learning improves audio classification models.
Paper proposes MTL for weakly labelled SED, improving performance with 2-step attention.
Acoustic scene classification is the task of identifying the scene from which the audio signal is recorded. Convolutional neural network (CNN) models are widely adopted with proven successes in acoustic scene classification. However, there is little insight on how an audio scene is perceived in CNN, as what have been d…
End-to-end DA method for domain-invariant CNNs using parallel audio recordings.
Spiking neural networks (SNNs) offer a promising alternative to current artificial neural networks to enable low-power event-driven neuromorphic hardware. Spike-based neuromorphic applications require processing and extracting meaningful information from spatio-temporal data, represented as series of spike trains over …
Adversarial audio attacks can be considered as a small perturbation unperceptive to human ears that is intentionally added to the audio signal and causes a machine learning model to make mistakes. This poses a security concern about the safety of machine learning models since the adversarial attacks can fool such model…
Neural nets classify Thai Lukthung songs from other genres.
Paper finds universal speech command perturbations that fool models.
End-to-end ASR error detection using audio-transcript entailment.