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.
Study improves animal audio classification using data augmentation.
Improved animated faces using audiovisual and modality dropout.
Speech-driven visual speech synthesis involves mapping features extracted from acoustic speech to the corresponding lip animation controls for a face model. This mapping can take many forms, but a powerful approach is to use deep neural networks (DNNs). However, a limitation is the lack of synchronized audio, video, an…
As the technology is advancing, audio recognition in machine learning is improved as well. Research in audio recognition has traditionally focused on speech. Living creatures (especially the small ones) are part of the whole ecosystem, monitoring as well as maintaining them are important tasks. Species such as animals …
Mapping states to actions in deep reinforcement learning is mainly based on visual information. The commonly used approach for dealing with visual information is to extract pixels from images and use them as state representation for reinforcement learning agent. But, any vision only agent is handicapped by not being ab…
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…
Study improves radio show segmentation using audio embeddings.
Deep learning classifies animal behavior from wearable accelerometers.
DIFNET tackles the suspended animation problem in deep graph neural networks.
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…
CNNs improve generalization to unseen audio devices with increased width, not depth.
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)…
Improved audio classification with limited labels using multitask and self-supervised learning.
A novel method compares 3D point clouds using information geometry.
Proposes COALA method for learning audio representations aligned with tags.
New neural network improves audio classification accuracy.
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.
Improved acoustic scene classification with factorized CNN.
Improved audio event recognition using audiovisual transformers.
The Morris Water Maze is commonly used in behavioural neuroscience for the study of spatial learning with rodents. Over the years, various methods of analysing rodent data collected in this task have been proposed. These methods span from classical performance measurements (e.g. escape latency, rodent speed, quadrant p…
Method learns audio embeddings with contextualized tags.
Self-paced ensemble learning improves audio classification models.
LISBET automates social behavior analysis using machine learning.
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.
Transformer model estimates keywords for better audio captioning.
System tackles indeterminacies in automated audio captioning.
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…
AHA model mimics animal episodic learning without labels.
Classifiers and beamforming algorithms improved audio surveillance detection accuracy.
We describe a novel weakly labeled Audio Event Classification approach based on a self-supervised attention model. The weakly labeled framework is used to eliminate the need for expensive data labeling procedure and self-supervised attention is deployed to help a model distinguish between relevant and irrelevant parts …
Paper finds universal speech command perturbations that fool models.
NeuroPaint infers missing brain area dynamics from multi-animal datasets.
End-to-end ASR error detection using audio-transcript entailment.
The development of models for learning music similarity and feature extraction from audio media files is an increasingly important task for the entertainment industry. This work proposes a novel music classification model based on metric learning and feature extraction from MP3 audio files. The metric learning process …
Study improves CNNs for audio scene classification by restricting receptive fields and adding frequency awareness.
FSD50K provides an open dataset of over 51k audio clips for sound event recognition.
This paper proposes a method for instrument classification in polyphonic music using monophonic data.
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…
Enhances ASC using time- and frequency-liked CNNs and bilinear pooling.
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 …
Neural network generates music scores directly from polyphonic audio.
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…
SVM classifier outperforms other models in classifying musical instruments from IRMAS data.
Music genre classification is a widely researched topic in music information retrieval (MIR). Being able to automatically tag genres will benefit music streaming service providers such as JOOX, Apple Music, and Spotify for their content-based recommendation. However, most studies on music classification have been done …