betaFeedback

WorksEngineering

AISHELL8-FISHEYE: A Fisheye Audio-Visual Dataset for Target Speaker Extraction with Distortion-Aware Baselines

Abstract

Fisheye cameras offer wide visual coverage but distort facial and lip geometry, challenging audio-visual target speaker extraction. We introduce AISHELL8-FISHEYE, a 47.03-hour corpus of 94 Mandarin speakers with synchronized audio and paired fisheye and normal-camera videos. Speaker-disjoint splits and synthetic two-speaker mixtures support reproducible evaluation under matched acoustic conditions. We also establish a baseline that combines a lip-reading encoder with a frozen distortion-aware branch transferred from fisheye head pose estimation. On fisheye video, adding this branch to an adapted lip encoder improves scale-invariant signal-to-distortion ratio improvement from 10.47 to 11.84 dB. The branch does not improve performance with a frozen lip encoder, highlighting the importance of visual adaptation. A substantial gap to paired normal-camera inputs remains. The corpus and baseline resources support further research on speech extraction from distorted visual cues.

Paper details

vlnc:W_sybbvhq9
Version
v1 · latest
Published
Fresh — added to the Hub within the last 30 days
Added
License
CC-BY-NC-SA-4.0
Usage

views · 0

downloads · 0

A view counts once per browser per day, a download each time the PDF is requested.

  • Engineering

Generative AI tools

View statement
Looking for related papers…