AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

BinauralGrad: A Two-Stage Conditional Diffusion Probabilistic Model for Binaural Audio Synthesis

Yichong Leng, Zehua Chen, Junliang Guo, Haohe Liu, Jiawei Chen, Xu Tan, Danilo Mandic, Lei He, Xiangyang Li, Tao Qin, sheng zhao, Tie-Yan Liu

NeurIPS 2022 · Image generation › Autoregressive and latent generation · approach: Diffusion audio synthesis · 29 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use two-stage (common then specific) instead of a single-stage diffusion model (ablation)BinauralGrad · Binaural speech benchmark testWave L2 (x10^-3): 0.144 -> 0.128Improved
use two-stage instead of single-stage diffusion (ablation)BinauralGrad · Binaural speech benchmark testPESQ: 2.544 -> 2.759Improved
use two-stage instead of single-stage diffusion (ablation)BinauralGrad · Binaural speech benchmark testMRSTFT: 1.269 -> 1.278No clear effect
use two-stage instead of single-stage diffusion (ablation)BinauralGrad · Binaural speech benchmark testPhase L2: 0.877 -> 0.837Improved
add second stage on top of stage 1 output (ablation)BinauralGrad · Binaural speech benchmark testWave L2 (x10^-3): 0.300 -> 0.128Improved
add first (common) stage output on top of physical warping (ablation)BinauralGrad · Binaural speech benchmark testWave L2 (x10^-3): 0.725 -> 0.300Improved
condition second stage on golden average instead of synthesized stage 1 output (ablation)BinauralGrad · Binaural speech benchmark testPESQ: 2.759 -> 4.212Improved
replace diffusion single stage baseline WarpNet with BinauralGradBinauralGrad · Binaural speech benchmark testWave L2 (x10^-3): 0.157 -> 0.128Improved
BinauralGrad vs WarpNet on spatial perceptionBinauralGrad · Binaural speech benchmark testSpatial MOS: 3.77 -> 3.79No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy