DeepAI
Log In Sign Up

DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressors

10/28/2020
by   Chandan K A Reddy, et al.
0

Human subjective evaluation is the gold standard to evaluate speech quality optimized for human perception. Perceptual objective metrics serve as a proxy for subjective scores. The conventional and widely used metrics require a reference clean speech signal, which is unavailable in real recordings. The no-reference approaches correlate poorly with human ratings and are not widely adopted in the research community. One of the biggest use cases of these perceptual objective metrics is to evaluate noise suppression algorithms. This paper introduces a multi-stage self-teaching based perceptual objective metric that is designed to evaluate noise suppressors. The proposed method generalizes well in challenging test conditions with a high correlation to human ratings.

READ FULL TEXT
10/05/2021

DNSMOS P.835: A Non-Intrusive Perceptual Objective Speech Quality Metric to Evaluate Noise Suppressors

Human subjective evaluation is the gold standard to evaluate speech qual...
07/15/2021

Objective Metrics to Evaluate Residual-Echo Suppression During Double-Talk

Human subjective evaluation is optimal to assess speech quality for huma...
06/27/2022

Audio Similarity is Unreliable as a Proxy for Audio Quality

Many audio processing tasks require perceptual assessment. However, the ...
03/08/2022

Practical cognitive speech compression

This paper presents a new neural speech compression method that is pract...
05/29/2021

DPLM: A Deep Perceptual Spatial-Audio Localization Metric

Subjective evaluations are critical for assessing the perceptual realism...
02/09/2021

CDPAM: Contrastive learning for perceptual audio similarity

Many speech processing methods based on deep learning require an automat...
05/04/2022

Does a PESQNet (Loss) Require a Clean Reference Input? The Original PESQ Does, But ACR Listening Tests Don't

Perceptual evaluation of speech quality (PESQ) requires a clean speech r...