PK PyTorchKR Papers
Papers with Code · CC BY-SA 4.0

Audio Classification

Classification › Audio Classification 204 평가 기록 29 datasets

Audio Classification is a machine learning task that involves identifying and tagging audio signals into different classes or categories. The goal of audio classification is to enable machines to automatically recognize and distinguish between different types of audio, such as music, speech, and environmental sounds.

개요는 각 항목의 일부입니다. 위 탭에서 전체 기록을 페이지별로 탐색할 수 있습니다.

벤치마크

Papers with Code 아카이브의 데이터셋별 기록 예시입니다. 평가 조건과 지표 방향이 검증되지 않아 순위를 의미하지 않습니다.

Dataset기록된 모델 예시MetricPaperCode
OmniVec2
Test mAP: 0.558
논문 -
OmniVec2
Top-1 Accuracy: 99.1PRE-TRAINING DATASET: MultipleAccuracy (5-fold): 99.1
논문 -
ADD
ICBHI Score: 65.53Sensitivity: 45.94Specificity: 85.13
논문 코드
Mirasol3B
Top 1 Accuracy: 69.8
논문 -
SHD
Event-SSM
Percentage correct: 95.9
논문 코드
ONE-PEACE
mAP: 69.7
논문 코드
EquiAV
Mean AP: 42.4
논문 코드
EAT
Accuracy: 98.3±0.04
논문 코드
SSC
Event-SSM
Accuracy: 88.4
논문 코드
EfficientLEAF (8s)
Accuracy: 72.2
논문 코드
CrissCross (AudioSet)
Top-1 Accuracy: 97PRE-TRAINING DATASET: AudioSet
논문 코드
Audiovisual Masked Autoencoder (Audiovisual, Single)
Top-1 Verb: 71.4Top-1 Noun: 56.4Top-1 Action: 46.0
논문 코드

데이터셋

29개
AudioSetESC-50ICBHI Respiratory Sound DatabaseVGGSoundSHDFSD50KBalanced Audio SetSpeech CommandsSSCBirdCLEF 2021DCASEEPIC-KITCHENS-100

논문

라이브러리

Papers with Code 리더보드 row에 연결된 구현 저장소입니다.

github.com/google-research/scenic 1 논문
github.com/google-research/scenic/tree/main/scenic/projects/av_mae 1 논문
github.com/vincenzodentamaro/aucoresnet 1 논문
github.com/alexandrosstergiou/PlayItBack 1 논문
github.com/cgaroufis/msspt 1 논문
github.com/cwx-worst-one/eat 1 논문
github.com/grigorisg9gr/polynomials-for-augmenting-nns 1 논문
github.com/jesperhauch/polynomial_deep_learning 1 논문

하위 태스크

ES Environmental Sound Classification 3 데이터셋 · 5 rows AM Audio Multiple Target Classification 0 데이터셋 · 0 rows PD Parkinson Detection from Speech 0 데이터셋 · 0 rows SA Semi-supervised Audio Classification 0 데이터셋 · 0 rows