CREMA-D: Speech Emotion Recognition Audio Re-recorded via ESP32-S3 MEMS Microphone

CREMA-D is a speech emotion recognition dataset. It appears to be a re-recording of the original audio files using an ESP32-S3 microcontroller with a MEMS microphone. The dataset is hosted on Kaggle, but detailed metadata about its size, format, and specific content is unavailable.

Use Cases

• Benchmarking emotion recognition models on audio captured with low-cost hardware (inferred from domain, verify after download)
• Studying the impact of microphone type and recording hardware on speech feature extraction (inferred from domain, verify after download)
• Training or fine-tuning models for multimodal emotion analysis (inferred from domain, verify after download)

Strengths

• Published on Kaggle, a major platform for data science.
• Builds upon the established CREMA-D dataset for speech emotion recognition.

Limitations

• Metadata is minimal; actual content requires verification after download.
• Row count, file formats, and column definitions are unknown, which limits suitability assessment.
• License and authorship details are unknown, affecting usage rights.

Provenance

Source

Kaggle

Collection Method

Likely a re-recording of the original CREMA-D audio samples using an ESP32-S3 MEMS microphone.