ASR WPM and Background Noise Evaluation: Controlled Audio Samples for Speech Recognition

Annotated audio recordings evaluate how speaking pace and background noise affect transcription accuracy for Whisper and other ASR systems. The dataset, created by danielrosehill, was last updated on December 9, 2025. Its specific size and row count are not provided in the available metadata.

Use Cases

• Benchmark ASR model robustness based on varied speaking paces like fast, slow, mumbled, and whispered speech
• Evaluate transcription accuracy degradation based on background noise types like cafe sounds, music, and traffic
• Compare performance of different ASR systems, such as Whisper, on controlled audio samples
• Analyze the impact of non-standard vocal characteristics, such as weird voices, on speech recognition

Strengths

• Dataset is explicitly designed for controlled evaluation of ASR performance factors
• Audio samples are annotated, which likely provides ground truth for accuracy measurement
• Covers multiple distinct noise environments and speaking styles as described

Limitations

• Column-level documentation is absent; field semantics must be inferred after download
• Row count is unknown, which may limit suitability assessment
• Description metadata is limited; actual data quality requires manual inspection after download

Provenance

Source

huggingface

Collection Method

Likely contains controlled audio recordings created or compiled for evaluation purposes.

Time Range

null

Freshness

Last updated 2025-12-09 18:19:17

Geography

null