AudioMNIST: Exploring Explainable Artificial Intelligence for audio analysis on a simple benchmark (2018-07-09T00:00:00.000000Z)

TL;DR

A novel Open Source audio dataset is presented consisting of 30,000 audio samples of English spoken digits which is used for classification tasks on spoken digits and speakers' biological sex and demonstrates the superior interpretability of audible explanations over visual ones in a human user study.

Authors

W. Samek

8 papers

Sören Becker

1 papers

Johanna Vielhaben

1 papers

M. Ackermann

1 papers

Klaus Müller

1 papers

S. Lapuschkin

2 papers

TL;DR

Authors

References49 items

Toward Explainable Artificial Intelligence for Precision Pathology.

Multi-dimensional concept discovery (MCD): A unifying framework with completeness guarantees

Interpreting mental state decoding with deep learning models

CoughLIME: Sonified Explanations for the Predictions of COVID-19 Cough Classifiers

From attribution maps to human-understandable explanations through Concept Relevance Propagation

Listen to Interpret: Post-hoc Interpretability for Audio Networks with NMF

Towards Sonification in Multimodal and User-friendlyExplainable Artificial Intelligence

Software for dataset-wide XAI: From local explanations to global insights with Zennit, CoRelAy, and ViRelAy

Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications

audioLIME: Listenable Explanations Using Source Separation

Deep Learning for ECG Analysis: Benchmarks and Insights from PTB-XL

Towards Novel Insights in Lattice Field Theory with Explainable Machine Learning

Explaining Machine Learning Models for Clinical Gait Analysis

Towards Best Practice in Explaining Neural Network Decisions with LRP

Unmasking Clever Hans predictors and assessing what machines really learn

Metrics for Explainable AI: Challenges and Prospects

iNNvestigate neural networks!

Interpreting and Explaining Deep Neural Networks for Classification of Audio Signals

Detecting and interpreting myocardial infarction using fully convolutional neural networks

Explaining Recurrent Neural Network Predictions in Sentiment Analysis

Interpretable Explanations of Black Boxes by Meaningful Perturbation

Very deep convolutional neural networks for raw waveforms

CNN architectures for large-scale audio classification

Quantum-chemical insights from deep tensor neural networks

Interpretable deep neural networks for single-trial EEG classification

“Why Should I Trust You?”: Explaining the Predictions of Any Classifier

Explaining nonlinear classification decisions with deep Taylor decomposition

Evaluating the Visualization of What a Deep Neural Network Has Learned

Intelligible Models for HealthCare: Predicting Pneumonia Risk and Hospital 30-day Readmission

On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation

Librispeech: An ASR corpus based on public domain audio books

ImageNet classification with deep convolutional neural networks

Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation

Speech Recognition by Machine, A Review

Unsupervised feature learning for audio classification using convolutional deep belief networks

How to Explain Individual Classification Decisions

Unsupervised Discovery of Nonlinear Structure Using Contrastive Backpropagation

DARPA TIMIT:: acoustic-phonetic continuous speech corpus CD-ROM, NIST speech disc 1-1.1

SWITCHBOARD: telephone speech corpus for research and development

LEMONS: Listenable Explanations for Music recOmmeNder Systems

How Can I Explain This to You? An Empirical Study of Deep Neural Network Explanation Methods

Explainable AI: Interpreting, Explaining and Visualizing Deep Learning

The layer-wise relevance propagation toolbox for artificial neural networks

FUNDAMENTAL TECHNOLOGIES IN MODERN SPEECH RECOGNITION Digital Object Identifier 10.1109/MSP.2012.2205597

Visualizing Higher-Layer Features of a Deep Network

The mnist database of handwritten digits

The frequency range of the voice fundamental in the speech of male and female adults

Fundamentals of speech recognition, Vol.

with Stochastic Gradient Descent with a batch size of 100 and constant momentum of 0.9 for 50,000 optimization steps with an initial learning rate of 0.0001 which was lowered

Field of Study

Journal Information

Name

Page

Volume

Venue Information

Name

Type

URL

Alternate Names