AirCaps Speaker ID
Speaker ID in
real-world noise.
A 17M-parameter speaker identification model evaluated on clean speech, environmental noise, and music.
One enrolled voice
Environmental noise and music
- Task
- Speaker ID
- Model size
- 17 million parameters
- Design target
- Real-world noisy speech
01
Model design
Noisy speech
Optimized for recordings with environmental noise and music.
17M parameters
Optimized for edge deployment through the Apple Neural Engine.
Three test variants
A clean baseline plus environmental noise and music.
02
Evaluation
Results across clean and noisy test sets.
EER comparison across the clean set and two noise categories.
Speaker identification benchmark
Overall · EER (%) · Lower is betterEqual error rate (EER). Noise results include only cases where noise is louder than speech: −10 and −5 dB source SNR. Overall is the unweighted mean of clean plus four noisy conditions.
03
Dataset
Hugging Face
Evaluation dataset
The dataset accompanying this evaluation includes clean, environmental noise, and music variants, plus an overall aggregate. The Hugging Face release contains the audio, labels, and test conditions used for the reported results.
Model access