Speech Command V-2

The 'Speech Command V-2' dataset is a benchmark that contains audio samples of spoken commands used to evaluate audio classification models.

Papers using Speech Command V-2 (3)

HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection2022 · 1 citesComposing General Audio Representation by Fusing Multilayer Features of a Pre-trained Model2022Cascaded Cross-Modal Transformer for Audio-Textual Classification2024