Research map / 3D vision / 3D generation
Who Called? V33DA: A Physically Verified Multimodal Benchmark for Vocal Attribution in Zebra Finch Groups
Maris Basha, Yuhang Wang, Xiaoran Chen, Longbiao Cheng, Luca N Yapura, Anja T Zai, Mathieu Salzmann, Richard Hahnloser
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Introduces V33DA, a physically verified multimodal benchmark for vocal attribution (identifying which zebra finch produced a vocalization and where) in group settings.
Problem
Identifying which group member produced a vocalization and localizing it is central to social communication studies but is rarely evaluated with physically verified ground truth; existing resources either localize sounds without identifying the caller or recognize individuals from isolated vocalizat
Approach
A multimodal benchmark that jointly evaluates caller identification and spatial localization in zebra finch groups using physically verified ground truth and 3D candidate geometry.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use a slot-indexed identity output head (SELDnet++ slot) | SELDnet++ · V33DA session-disjoint vs leave-one-bird-out | top-1 attribution accuracy (%): 86.5 -> 0.0 | Hurt |
| attribute through localization instead of directly with slot head (ablation) | AudioANN · V33DA leave-one-bird-out | top-1 attribution accuracy (%): 0.0 -> 53.0 | Improved |
| remove microphones from the array (ablation) | SpatialScorer · V33DA leave-one-bird-out | top-1 attribution accuracy (%): 51.2 -> 26.0 | Hurt |
| permute microphone channels (ablation) | ACCDOA · V33DA session-disjoint | top-1 attribution accuracy (%): 64.3 -> 38.8 | Hurt |
| zero audio at test time (ablation) | ACCDOA and EINV2 · V33DA LOO / held-out BP01 / BP02 | accuracy change (points): -27.4 and -26.4 on LOO | Hurt |
| shuffle candidate geometry across events (ablation) | ACCDOA and EINV2 · V33DA LOO / held-out BP01 / BP02 | accuracy change (points): -29.0 and -26.9 on LOO | Hurt |
| zero radio features at test time (ablation) | ACCDOA and EINV2 · V33DA LOO / held-out BP01 / BP02 | accuracy change (points): +0.0 | No clear effect |
| zero radio features at test time (ablation) | SpatialScorer · V33DA held-out BP05 | accuracy change (points): -14.8 on BP05; +6.3 on LOO | Mixed |
| add candidate conditioning without spatial reasoning (SELDnet++ open, PairRank, Whisper candidate, CST-former) | candidate-scoring baselines · V33DA leave-one-bird-out | top-1 attribution accuracy (%): below 27.0 random reference | No clear effect |
| smaller distance between vocalizer and nearest competing bird (below 10 cm vs above 50 cm) | ACCDOA · V33DA LOO | top-1 attribution accuracy (%): 73.0 -> 46.6 | Hurt |
| physics-only SRP +-20 vs learned slot model under transfer | SRP +-20 · V33DA leave-one-bird-out | top-1 attribution accuracy (%): 0.0 -> 53.5 | Improved |
| per-experiment color gallery, outlier removal, occlusion filtering, 48x augmentation (ablation) | K-NN backpack color classifier · 15 BirdPark experiments | color accuracy (%): 88.9% -> 96.4% | Improved |
Experimental setup
Benchmarks: V33DA
Closest papers by meaning
- Vocal Call Locator Benchmark (VCL) for localizing rodent vocalizations from multi-channel audio (NeurIPS 2024 · similarity 0.88)
- OpenWhistle: A Large-Scale Longitudinal Dataset and Benchmark of Bottlenose Dolphin Vocalizations (NeurIPS 2026 · similarity 0.86)
- NatureLM-audio: an Audio-Language Foundation Model for Bioacoustics (ICLR 2025 · similarity 0.84)
- RealBirdID: Benchmarking Bird Species Identification in the Era of MLLMs (CVPR 2026 · similarity 0.84)
- The iNaturalist Sounds Dataset (NeurIPS 2024 · similarity 0.82)
- Meow-Omni 1: A Multimodal Large Language Model for Feline Ethology (NeurIPS 2026 · similarity 0.82)
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.
