The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Speech Quality and Testing Framework

Abstract

The INTERSPEECH 2020 Deep Noise Suppression Challenge is intended to promote collaborative research in real-time single-channel Speech Enhancement aimed to maximize the subjective (perceptual) quality of the enhanced speech. A typical approach to evaluate the noise suppression methods is to use objective metrics on the test set obtained by splitting the original dataset. Many publications report reasonable performance on the synthetic test set drawn from the same distribution as that of the training set. However, often the model performance degrades significantly on real recordings. Also, most of the conventional objective metrics do not correlate well with subjective tests and lab subjective tests are not scalable for a large test set. In this challenge, we open-source a large clean speech and noise corpus for training the noise suppression models and a representative test set to real-world scenarios consisting of both synthetic and real recordings. We also open source an online subjective test framework based on ITU-T P.808 for researchers to quickly test their developments. The winners of this challenge will be selected based on subjective evaluation on a representative test set using P.808 framework.

Details about Deep Noise Suppression Challenge

References in corpus (2)

• Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation
• An individualized super Gaussian single microphone Speech Enhancement for hearing aid users with smartphone as an assistive device

Cited by in corpus (23)

• An Open source Implementation of ITU-T Recommendation P.808 with Validation
• Self-attending RNN for Speech Enhancement to Improve Cross-corpus Generalization
• Asteroid: the PyTorch-based audio source separation toolkit for researchers
• Exploring the Best Loss Function for DNN-Based Low-latency Speech Enhancement with Temporal Convolutional Networks
• Augmented Datasheets for Speech Datasets and Ethical Decision-Making
• Online Monaural Speech Enhancement Using Delayed Subband LSTM
• NORESQA: A Framework for Speech Quality Assessment using Non-Matching References
• Real-time Monaural Speech Enhancement With Short-time Discrete Cosine Transform
• End-to-End Complex-Valued Multidilated Convolutional Neural Network for Joint Acoustic Echo Cancellation and Noise Suppression
• Boosting Objective Scores of a Speech Enhancement Model by MetricGAN Post-processing
• FullSubNet: A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech Enhancement
• Complex Spectral Mapping With Attention Based Convolution Recurrent Neural Network for Speech Enhancement
• DPLM: A Deep Perceptual Spatial-Audio Localization Metric
• Phase-aware Single-stage Speech Denoising and Dereverberation with U-Net
• Improving Frame-Online Neural Speech Enhancement with Overlapped-Frame Prediction
• Deep Noise Suppression With Non-Intrusive PESQNet Supervision Enabling the Use of Real Training Data
• Sequence to Multi-Sequence Learning via Conditional Chain Mapping for Mixture Signals
• A Pyramid Recurrent Network for Predicting Crowdsourced Speech-Quality Ratings of Real-World Signals
• Perceptual-based deep-learning denoiser as a defense against adversarial attacks on ASR systems
• Distortion-controlled Training for End-to-end Reverberant Speech Separation with Auxiliary Autoencoding Loss
• Incorporating Real-world Noisy Speech in Neural-network-based Speech Enhancement Systems
• CLC: Complex Linear Coding for the DNS 2020 Challenge
• The IOA System for Deep Noise Suppression Challenge using a Framework Combining Dynamic Attention and Recursive Learning