CREMA-D: Per-Emotion Speech Recognition Performance on 1,488 Samples

Per-emotion performance on CREMA-D (cross-corpus, 1,488 samples). The dataset was authored by Mohammed Tawfik and last updated on May 7, 2026. It is a 5.5 KB Excel file available under a CC-BY-4.0 license on figshare.

Use Cases

• Benchmarking speech emotion recognition models based on per-emotion performance metrics.
• Analyzing model generalization across different corpora based on the cross-corpus evaluation mentioned.
• Comparing the difficulty of recognizing specific emotions from speech based on the reported performance scores.

Strengths

• Provides performance metrics for 1,488 samples.
• Uses a cross-corpus evaluation approach, which may test generalization.
• Has a clear license (CC-BY-4.0) for reuse.

Limitations

• The dataset is very small at 5.5 KB, indicating limited scope.
• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.

Provenance

Source

figshare, author Mohammed Tawfik

Freshness

Last updated 2026-05-07 17:45:46; freshness should be verified.