paper-with-me

Audio Classification 벤치마크

Audio Classification on Speech Commands

14개 결과 · ⬇ CSV · JSON

Accuracy

95.1 95.9 96.7 97.5 98.3 2021-04 2026-09 AST-S — 98.11 (2021-04-05) AST-S — 98.11 (2021-04-05) PDC — 97.8 (2021-04-16) PDC — 97.8 (2021-04-16) EfficientLEAF — 95.2 (2022-07-12) LEAF — 95.1 (2022-07-12) melspect — 95.1 (2022-07-12) EfficientLEAF — 95.2 (2022-07-12) LEAF — 95.1 (2022-07-12) melspect — 95.1 (2022-07-12) EAT — 98.3 (2024-01-07) EAT — 98.3 (2024-01-07) ASM-RH — 96.51 (2024-02-28) ASM-RH — 96.51 (2024-02-28) AST-S — 98.11 (2021-04-05) EAT — 98.3 (2024-01-07)
RankModel Accuracy Extra Training Data PaperCodeYear
1 EAT 98.3±0.04 ✓ EAT: Self-Supervised Pre-Training with Efficient Audio Transformer cwx-worst-one/eat 2024
2 AST-S 98.11±0.05 AST: Audio Spectrogram Transformer YuanGongND/ast · nttcslab/composing-general-audio-repr · pxaris/ccml · +2 2021
3 PDC 97.8 Augmenting Deep Classifiers with Polynomial Neural Networks grigorisg9gr/polynomials-for-augmenting-nns · jesperhauch/polynomial_deep_learning 2021
4 ASM-RH 96.51 Mixer is more than just a model 2024
5 EfficientLEAF 95.2 EfficientLEAF: A Faster LEarnable Audio Frontend of Questionable Use cpjku/efficientleaf 2022
6 LEAF 95.1 EfficientLEAF: A Faster LEarnable Audio Frontend of Questionable Use cpjku/efficientleaf 2022
6 melspect 95.1 EfficientLEAF: A Faster LEarnable Audio Frontend of Questionable Use cpjku/efficientleaf 2022
8 EAT 98.3±0.04 ✓ EAT: Self-Supervised Pre-Training with Efficient Audio Transformer cwx-worst-one/eat 2024
9 AST-S 98.11±0.05 AST: Audio Spectrogram Transformer YuanGongND/ast · nttcslab/composing-general-audio-repr · pxaris/ccml · +2 2021
10 PDC 97.8 Augmenting Deep Classifiers with Polynomial Neural Networks grigorisg9gr/polynomials-for-augmenting-nns · jesperhauch/polynomial_deep_learning 2021
1–10 / 14 다음 → 페이지당 10 20 50 100