HyperAIHyperAI

Command Palette

Search for a command to run...

5 months ago

SSAST: Self-Supervised Audio Spectrogram Transformer

Yuan Gong Cheng-I Jeff Lai Yu-An Chung James Glass

SSAST: Self-Supervised Audio Spectrogram Transformer

Abstract

Code Repositories

YuanGongND/ast
pytorch
Mentioned in GitHub
YuanGongND/ssast
Official
pytorch
Mentioned in GitHub
siavashshams/ssamba
pytorch
Mentioned in GitHub

Benchmarks

BenchmarkMethodologyMetrics
audio-classification-on-balanced-audio-setSSAST-PATCH
Mean AP: 31.0
audio-classification-on-balanced-audio-setSSAST-FRAME
Mean AP: 29.2
speaker-identification-on-voxceleb1SSAST-PATCH
Accuracy: 64.2
Top-1 (%): 64.2
speaker-identification-on-voxceleb1SSAST-FRAME
Accuracy: 80.8
Top-1 (%): 80.8
spoken-command-recognition-on-speech-commandSSAST-PATCH
Accuracy: 98.0
spoken-command-recognition-on-speech-commandSSAST-FRAME
Accuracy: 98.1

Build AI with AI

From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.

AI Co-coding
Ready-to-use GPUs
Best Pricing
Get Started

Hyper Newsletters

Subscribe to our latest updates
We will deliver the latest updates of the week to your inbox at nine o'clock every Monday morning
Powered by MailChimp