Convolutional Recurrent Neural Networks for Polyphonic Sound Event Detection

Giambattista Parascandolo, Toni Heittola, Heikki Huttunen, +1

IEEE/ACM Transactions on Audio Speech and Language Processing

Recurrent neural networks for polyphonic sound event detection in real life recordings

Giambattista Parascandolo, Heikki Huttunen, Tuomas Virtanen

MusicEngineeringMachine LearningRecurrent Neural NetworkAcoustic Modeling +15

Avoiding Discrimination through Causal Reasoning

Niki Kilbertus, Mateo Rojas-Carulla, Giambattista Parascandolo, +3

arXiv (Cornell University)

EngineeringMachine LearningDiscriminationCausal InferenceData Science +15

Convolutional recurrent neural networks for bird audio detection

Sharath Adavanne, Giambattista Parascandolo, Konstantinos Drossos, +1

Convolutional Neural NetworkEngineeringMachine LearningAcoustic ModelingSpeech Recognition +14

Sound Event Detection in Multichannel Audio Using Spatial and Harmonic Features

Sharath Adavanne, Giambattista Parascandolo, Pasi Pertilä, +2

arXiv (Cornell University)

MusicEngineeringRecurrent Neural NetworkAcoustic ModelingHarmonic Features +15

Learning Independent Causal Mechanisms

Giambattista Parascandolo, Niki Kilbertus, Mateo Rojas-Carulla, +1

MPG.PuRe (Max Planck Society)

Artificial IntelligenceEngineeringMachine LearningCausal InferenceGenerative System +18

A convolutional neural network approach for acoustic scene classification

Michele Valenti, Stefano Squartini, Aleksandr Diment, +2

Learning explanations that are hard to vary

Giambattista Parascandolo, Alexander Neitz, Antonio Orvieto, +2

arXiv (Cornell University)

Artificial IntelligenceEngineeringMachine LearningAutoencodersNatural Language Processing +15

Taming the waves: sine as activation function in deep neural networks

Giambattista Parascandolo, Heikki Huttunen, Tuomas Virtanen

Sinusoidal ActivationsActivation FunctionPeriodic CyclesDeep Neural NetworksEngineering +13

Low latency sound source separation using convolutional recurrent neural networks

Gaurav Naithani, Tom Barker, Giambattista Parascandolo, +3

MusicSource SeparationEngineeringMachine LearningSpeech Enhancement +15