A new method to decompose audio scenes using deep learning.
problem Understanding audio scenes with random microphone arrangements.
method Formulated a neural network for nonnegative tensor factorization.
result Learned sources' individual spectral dictionaries and activation patterns.
Improved acoustic scene classification with factorized CNN.
problem Acoustic scene classification in varying environments.
method Large-margin factorized CNN with triplet loss.
result Improved performance and better generalization on unseen data.
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.
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…
CNNs improve generalization to unseen audio devices with increased width, not depth.
problem CNNs are sensitive to specific audio recording devices in acoustic scene classification.
method Investigated the relationship between over-parameterization and generalization in CNNs for audio classification.
result Increasing width improves generalization to unseen devices without increasing the number of parameters.
Study improves CNNs for audio scene classification by restricting receptive fields and adding frequency awareness.
problem Improving CNNs for robust acoustic scene classification.
method Investigated different receptive field configurations for various CNN architectures and introduced Frequency Aware CNNs.
result Several well-performing submissions to DCASE 2019 Challenge were achieved.
Separating an audio scene into isolated sources is a fundamental problem in computer audition, analogous to image segmentation in visual scene analysis. Source separation systems based on deep learning are currently the most successful approaches for solving the underdetermined separation problem, where there are more …
Enhances ASC using time- and frequency-liked CNNs and bilinear pooling.
problem Improving acoustic scene classification accuracy.
method Harmonic and percussive source separation, two-stream CNN architecture, bilinear pooling.
result Improved accuracy on DCASE 2019 sub task 1a dataset.
End-to-end DA method for domain-invariant CNNs using parallel audio recordings.
problem Distribution mismatches between training and application data in machine listening.
method Enforcing equal hidden layer representations for domain-parallel samples.
result Learn domain-invariant classifiers without requiring classification labels.
New method separates music vocals from accompaniment without labeled data.
problem Separating music sources without isolated recordings.
method Bootstrapping deep model using primitive auditory cues.
result Trained deep model separates vocals from accompaniment in unlabeled music.
In acoustic scene classification researches, audio segment is usually split into multiple samples. Majority voting is then utilized to ensemble the results of the samples. In this paper, we propose a punishment voting algorithm based on the super categories construction method for acoustic scene classification. Specifi…
Paper presents an audiovisual model to recognize sounds from weakly labeled video data.
problem Sound recognition from weakly labeled video data.
method Audiovisual fusion model with attention mechanism.
result The model achieves a mean Average Precision (mAP) of 46.16 on AudioSet, outperforming state-of-the-art models.
System tackles indeterminacies in automated audio captioning.
problem Word selection and sentence length indeterminacies in automated audio captioning.
method Solves caption generation and sub-indeterminacy problems through multi-task learning to estimate keywords and sentence length.
result Model achieved 20.7 SPIDEr score, significantly outperforming baseline.
In the past, Acoustic Scene Classification systems have been based on hand crafting audio features that are input to a classifier. Nowadays, the common trend is to adopt data driven techniques, e.g., deep learning, where audio representations are learned from data. In this paper, we propose a system that consists of a …
Improved deep CNNs for ASC by optimizing receptive field size.
problem Deep CNNs perform poorly in ASC compared to simpler models.
method Analyzed and adapted the receptive field of ResNet and DenseNet.
result State-of-the-art performance achieved with optimized receptive field.
The ability to decompose scenes in terms of abstract building blocks is crucial for general intelligence. Where those basic building blocks share meaningful properties, interactions and other regularities across scenes, such decompositions can simplify reasoning and facilitate imagination of novel scenarios. In particu…
Data clustering has received a lot of attention and numerous methods, algorithms and software packages are available. Among these techniques, parametric finite-mixture models play a central role due to their interesting mathematical properties and to the existence of maximum-likelihood estimators based on expectation-m…
A new neural network learns from acoustic scenes by suppressing irrelevant patterns.
problem Acoustic scenes are rich and redundant, making classification challenging.
method Spatio-temporal attention pooling layer coupled with a convolutional recurrent neural network.
result The method outperforms a strong convolutional neural network baseline and sets new state-of-the-art performance.
The group affect or emotion in an image of people can be inferred by extracting features about both the people in the picture and the overall makeup of the scene. The state-of-the-art on this problem investigates a combination of facial features, scene extraction and even audio tonality. This paper combines three addit…
A multi-head attention network improves ASC by recognizing overlapping sound patterns.
problem Challenging ASC due to overlapping sound patterns and complex event mixtures.
method Proposes a multi-head attention network to model complex temporal input structures.
result Achieved competitive performance on DCASE 2018 Task 5 dataset.
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,…
In this paper we study the problem of acoustic scene classification, i.e., categorization of audio sequences into mutually exclusive classes based on their spectral content. We describe the methods and results discovered during a competition organized in the context of a graduate machine learning course; both by the st…
GENESIS generates and samples 3D scenes by capturing object interactions.
problem Lack of models that explicitly capture object interactions in scene generation.
method Object-centric latent variables, spatial GMM, amortized inference, autoregressive prior.
result First object-centric generative model of 3D visual scenes.
AV-ASR system improves speech recognition with visual context.
problem Improving speech recognition accuracy with visual information.
method Transformer-based architecture with multiresolution and multimodal training.
result Multiresolution training speeds up convergence and improves WER by 18%.
Study shows bottlenecks improve image segmentation quality.
problem Robust object discovery in real-world images remains challenging.
method Empirical investigation of reconstruction bottlenecks in GENESIS model.
result Reconstruction bottlenecks determine reconstruction and segmentation quality.
RICH models scenes as hierarchical tree to learn and generate complex compositions.
problem Learning compositional structures between parts and objects in natural scenes.
method RICH uses a latent scene graph to organize entities into a tree structure and employs a top-down inference approach.
result RICH learns and generates complex scene hierarchies from unlabeled data.
Paper tackles GAN instability in audio and speech signals using a new similarity metric.
problem Improving stability of LS-GANs for audio and speech signals.
method Proposes a new similarity metric in unitary space of Schur decomposition for 2D audio and speech representations.
result Enhanced stability in training with less mode collapse compared to baseline GANs.
We propose the product-of-filters (PoF) model, a generative model that decomposes audio spectra as sparse linear combinations of "filters" in the log-spectral domain. PoF makes similar assumptions to those used in the classic homomorphic filtering approach to signal processing, but replaces hand-designed decompositions…
SPACE models complex scenes by decomposing objects and backgrounds.
problem Scalability and unsupervised object-oriented scene representation learning.
method Generative latent variable model combining spatial-attention and scene-mixture approaches.
result SPACE achieves factorized object representations and decomposes complex scenes.
In this work, we derive a generic overcomplete frame thresholding scheme based on risk minimization. Overcomplete frames being favored for analysis tasks such as classification, regression or anomaly detection, we provide a way to leverage those optimal representations in real-world applications through the use of thre…
Generates coherent 3D scenes from monocular videos without supervision.
problem Lack of 3D scene modeling in video generation models.
method Trains a model to generate 3D scenes with moving objects and a background from monocular videos.
result Trained model generates coherent 3D scenes with multiple moving objects and a background.
A new method for estimating joint value functions in multi-scene reinforcement learning.
problem High variance in samples for policy gradient computations in multi-scene environments.
method Sparse attention mechanism over multiple value function hypotheses to approximate the true joint value function.
result Significant improvements in reward scores and enhanced navigation efficiency across OpenAI ProcGen environments.
This work presents a novel approach for robust PCA with total variation regularization for foreground-background separation and denoising on noisy, moving camera video. Our proposed algorithm registers the raw (possibly corrupted) frames of a video and then jointly processes the registered frames to produce a decomposi…
This work proposes a method to compose visual relations more faithfully.
problem Composing relations between objects in images is challenging due to their entanglement.
method Represent each relation as an unnormalized density (energy-based model) to compose relations factorizedly.
result The proposed method generates and edits scenes with multiple sets of relations more faithfully.
Generates music with video emotion using deep neural networks.
problem Generating music with video emotion.
method Hybrid deep neural network combining ANFIS and LSTM.
result Low mean absolute errors and similar global features in spectrograms.
We introduce the task of acoustic question answering (AQA) in the area of acoustic reasoning. In this task an agent learns to answer questions on the basis of acoustic context. In order to promote research in this area, we propose a data generation paradigm adapted from CLEVR (Johnson et al. 2017). We generate acoustic…
Paper improves video categorization using temporal coherence.
problem Video categorization in multiple modalities.
method Temporal coherence-based regularization for multimodal models.
result Models with temporal coherence outperform state-of-the-art.
OtoWorld helps agents learn to navigate by listening in interactive environments.
problem Training agents to navigate using auditory information.
method Interactive environment with agents learning to listen and navigate.
result Agents can win at OtoWorld, a navigation game with sound sources.
New approach uses dynamic programming to efficiently discover failures in autonomous vehicle simulations.
problem Efficiently discovering rare failure events in autonomous vehicle simulations.
method Approximate dynamic programming and scene decomposition to estimate failure distribution.
result Increased number of failures discovered compared to baseline approaches.
Generative Adversarial Networks (GANs) can produce images of remarkable complexity and realism but are generally structured to sample from a single latent source ignoring the explicit spatial interaction between multiple entities that could be present in a scene. Capturing such complex interactions between different ob…
A neural scene representation framework enforcing 3D transformations.
problem Learning 3D scene representations from images without 3D supervision.
method Introducing a loss enforcing equivariance of the scene representation with 3D transformations.
result Real-time neural rendering with comparable results to models requiring minutes for inference.
Efficient model for foggy scene understanding in vehicles.
problem Challenging scene understanding and segmentation under foggy conditions.
method Domain adaptation and illumination-invariant image transformation.
result Outperforms state-of-the-art models in foggy scene understanding.
Scene text magnifier enhances readability for visually impaired.
problem Helps visually impaired read natural scene text.
method Four CNN-based networks: character erasing, extraction, magnify, synthesis.
result Effective text magnification without background alteration.
New model separates objects in scenes, enabling novel arrangements and depth.
problem Lack of modular, compositional scene modeling in generative models.
method Ensemble of generative models (experts) compete for explaining different parts of a scene.
result Model generates scenes with novel object arrangement and depth ordering.
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.
ROOTS learns to represent and render 3D scenes with object-centric models.
problem Learning to represent and render 3D scenes with object-centric compositionality.
method Probabilistic generative model for learning object representations and scene rendering from partial observations.
result The model can infer 3D object representations and render scenes from arbitrary viewpoints.