CAS_EEG: EEG-Audio Paired Data for Auditory Target Detection

CAS_EEG is a paired EEG-audio dataset for studying auditory target detection under continuous background noise. The dataset covers the full pipeline from source audio and stimulus-generation scripts to participant-level raw and preprocessed EEG data. It was created by author 'jatshi' and was last updated on the Hugging Face platform in April 2026.

Use Cases

• Training models for auditory target detection based on EEG signals and paired audio stimuli.
• Studying neural responses to overlapping auditory events and background noise.
• Developing preprocessing and alignment pipelines for EEG-audio data.
• Benchmarking models for continuous auditory scene analysis.

Strengths

• Covers the full pipeline from source audio to final aligned EEG-audio samples.
• Includes raw and preprocessed EEG data at the participant level.
• Stimulus streams are 120 seconds long, containing target, non-target, and overlapping events.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count, file formats, and license information are unknown.
• Description metadata is limited; actual data quality requires manual inspection after download.

Provenance

Source

Hugging Face dataset by author 'jatshi'.

Collection Method

Collected from participants listening to 120-second auditory stimulus streams.

Freshness

Last updated 2026-04-15 04:24:41; freshness should be verified.