Search Results for author:
Found 6 papers, 4 papers with code
Aura: Privacy-preserving Augmentation to Improve Test Set Diversity in Speech Enhancement
Noise suppression models running in production environments are commonly trained on publicly available datasets.
Lumos: A Library for Diagnosing Metric Regressions in Web-Scale Applications
Web-scale applications can ship code on a daily to weekly cadence.
The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Testing Framework, and Challenge Results
In this challenge, we open-sourced 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.
The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Speech Quality and Testing Framework
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.
A scalable noisy speech dataset and online subjective test framework
Our subjective MOS evaluation is the first large scale evaluation of Speech Enhancement algorithms that we are aware of.
On Design of Problem Token Questions in Quality of Experience Surveys
Based on 900, 000 calls gathered using a randomized controlled experiment from a live system, we find that the order bias can be significantly reduced by randomizing the display order of tokens.
