Cases/EV/C11
EV / New EnergyOEM sound-quality teams + Tier 2 trim / HVAC / door locks

EV Cabin "Small Sounds" Sound-Quality Evaluation

01

Pain Points

  • !Without engine masking, an EV amplifies and exposes door-closing, air-vent, and rattle sounds.
  • !Transient events must be detected accurately before evaluation; manual segmentation is unreliable.
  • !Subjective "cheapness" complaints lack objective quantification and a basis for regression.
02

The Tinia Approach

Auto-locate transient events + four-metric psychoacoustic characterization; with subjective ratings, use AutoML to predict the "premium/cheap" tendency.

Capture transient eventsLoudness + Sharpness + Roughness + TonalityFeature mergeAutoML discrimination (optional)
03

Nodes Used

Active Segment Detectionactive_segment
Auto-locate transient sound events
Loudnessloudness
Event loudness
Sharpnesssharpness
Event sharpness
Roughnessroughness
Event roughness
Tonalitytonality
Event tonality
Feature Mergefeature_merge
Merge features across events

Core nodes; add or remove steps as needed for your data and standards — the node graph is always editable.

04

Expected Output

  • Psychoacoustic metrics for each sound event.
  • A subjective-objective regression discriminant function (AutoML distillation, optional).
  • An objective basis for quantifying "small sound" issues.
Reference Standards / Engineering PracticeOEM internal standards · ECMA-418-2

Want to run this workflow on your own data?

Request a Trial
EV

Other cases in this domain