Time Series Analysis on Speech Commands

Metric: % Test Accuracy (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Sort:

#	Model↕	% Test Accuracy▼	Extra Data	Paper	Date↕	Code
1	SepTr	98.51	No	SepTr: Separable Transformer for Audio Spectrogr...	2022-03-17	Code
2	ViT	98.11	No	AST: Audio Spectrogram Transformer	2021-04-05	Code
3	FlexTCN-4	97.73	No	FlexConv: Continuous Kernel Convolutions with Di...	2021-10-15	Code
4	MatchboxNet	97.4	No	MatchboxNet: 1D Time-Channel Separable Convoluti...	2020-04-21	Code
5	CKCNN (100k)	95.27	No	CKConv: Continuous Kernel Convolution For Sequen...	2021-02-04	Code

#1SepTrSOTA
98.51
% Test Accuracy· 2022-03-17
SepTr: Separable Transformer for Audio Spectrogram Processing Code
#2ViTSOTA
98.11
% Test Accuracy· 2021-04-05
AST: Audio Spectrogram Transformer Code
#3FlexTCN-4
97.73
% Test Accuracy· 2021-10-15
FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes Code
#4MatchboxNetSOTA
97.4
% Test Accuracy· 2020-04-21
MatchboxNet: 1D Time-Channel Separable Convolutional Neural Network Architecture for Speech Commands Recognition Code
#5CKCNN (100k)
95.27
% Test Accuracy· 2021-02-04
CKConv: Continuous Kernel Convolution For Sequential Data Code