• Publications
  • Influence
Convolutional Recurrent Neural Networks for Polyphonic Sound Event Detection
TLDR
We combine CNN and RNN in a convolutional recurrent neural network (CRNN) and apply it on a polyphonic SED task. Expand
Recurrent neural networks for polyphonic sound event detection in real life recordings
TLDR
We present an approach to polyphonic sound event detection in real life recordings based on bi-directional long short term memory (BLSTM) recurrent neural networks (RNNs), trained to map acoustic features of a mixture signal consisting of sounds from multiple classes, to binary activity indicators of each event class. Expand
Avoiding Discrimination through Causal Reasoning
TLDR
We frame the problem of discrimination based on protected attributes in the language of causal reasoning and propose natural causal non-discrimination criteria. Expand
Sound Event Detection in Multichannel Audio Using Spatial and Harmonic Features
TLDR
We propose the use of spatial and harmonic features in combination with long short term memory (LSTM) recurrent neural network (RNN) for automatic sound event detection (SED) task. Expand
DCASE 2016 ACOUSTIC SCENE CLASSIFICATION USING CONVOLUTIONAL NEURAL NETWORKS
This workshop paper presents our contribution for the acoustic scene classification (ASC) task proposed for the “detection and classification of acoustic scenes and events” (DCASE) 2016 challenge. WeExpand
Convolutional recurrent neural networks for bird audio detection
TLDR
We propose using convolutional recurrent neural networks on the task of automated bird audio detection in real-life environments. Expand
Learning explanations that are hard to vary
TLDR
We show that averaging gradients across examples -- akin to a logical OR of patterns -- can favor memorization and `patchwork' solutions that sew together different strategies, instead of identifying invariances. Expand
Learning Independent Causal Mechanisms
TLDR
We develop an algorithm to recover a set of independent (inverse) mechanisms from transformed data points. Expand
Taming the waves: sine as activation function in deep neural networks
Most deep neural networks use non-periodic and monotonic—or at least quasiconvex— activation functions. While sinusoidal activation functions have been successfully used for specific applications,Expand
A convolutional neural network approach for acoustic scene classification
TLDR
This paper presents a novel application of convolutional neural networks (CNNs) for the task of acoustic scene classification (ASC). Expand
...
1
2
...