DeepAI AI Chat
Log In Sign Up

A Differentiable Perceptual Audio Metric Learned from Just Noticeable Differences

by   Pranay Manocha, et al.

Assessment of many audio processing tasks relies on subjective evaluation which is time-consuming and expensive. Efforts have been made to create objective metrics but existing ones correlate poorly with human judgment. In this work, we construct a differentiable metric by fitting a deep neural network on a newly collected dataset of just-noticeable differences (JND), in which humans annotate whether a pair of audio clips are identical or not. By varying the type of differences, including noise, reverb, and compression artifacts, we are able to learn a metric that is well-calibrated with human judgments. Furthermore, we evaluate this metric by training a neural network, using the metric as a loss function. We find that simply replacing an existing loss with our metric yields significant improvement in denoising as measured by subjective pairwise comparison.


SAQAM: Spatial Audio Quality Assessment Metric

Audio quality assessment is critical for assessing the perceptual realis...

CDPAM: Contrastive learning for perceptual audio similarity

Many speech processing methods based on deep learning require an automat...

A novel fuzzy logic-based metric for audio quality assessment: Objective audio quality assessment

ITU-R BS.1387 states a method for objective assessment of perceived audi...

Perceptual audio loss function for deep learning

PESQ and POLQA , are standards are standards for automated assessment of...

DPLM: A Deep Perceptual Spatial-Audio Localization Metric

Subjective evaluations are critical for assessing the perceptual realism...

Audio Similarity is Unreliable as a Proxy for Audio Quality

Many audio processing tasks require perceptual assessment. However, the ...

DHASP: Differentiable Hearing Aid Speech Processing

Hearing aids are expected to improve speech intelligibility for listener...

Code Repositories


Perceptual Metrics of Audio - perceptually relevant loss function. DPAM and CDPAM

view repo