HyperAIHyperAI

Command Palette

Search for a command to run...

Audiodatenklassifizierung und Sound Event Detection (SED)

Klassifizieren von Audioschnipseln in Kategorien und Erkennen spezifischer Klangereignisse innerhalb von Audioaufzeichnungen (z. B. zerbrechendes Glas, Hundebellen).

Leaderboard

Insgesamt 12 Modelle

Benchmarks

esc-50
BEATs
ICBHI Respiratory Sound Database
BTS
AudioSet
FSD50k
Speech Commands
EAT
YouTube News dataset (White Noise)
Inception-v3 CRNN
ssc
Event-SSM
YouTube News dataset (No Noise)
Inception-v3 CRNN
audiocaps
Audio Flamingo (4-shot)
BirdCLEF 2021
VoxForge
LEAF
Untranscribed mixed-speech dataset
SVM
DCASE
CrissCross (AudioSet)
AudioSet-2M
AudioSet-20K
L3DAS21
PHC SEDnet n=2
yeast
ToxiAlert-Bench
SCENE
IndicTTS
A3Lab PASCAL CHiME
crema-d
UrbanSound8K
AudioCLIP
Emotions
Sidewalk Material Dataset
RealSync
ravdess
Pascal
vocalsound
VocalSound Baseline
Espgame
Corel5k
YouTube News dataset (Background Music)
YouTube News dataset (Crackling Noise)
Inception-v3 CRNN
VOC07
VGGSound
Sarcasm
CREMAD
Universal Dependencies
Twitter
TUT Urban Acoustic Scenes 2018
ERGL: event relational graph representation learning
SWBD
DCASE 2019 Mobile
Basic + Spectrum Correction
BACKSpeech
3Sources
epic-sounds
IAPRTC12
RWCP Sound Scene Database
STL-SNN
opensubtitles
Apple bi-LSTM
OpenETD
NVGesture
Nordic Language Identification
FastText
MIRFlickr
MHClip-Y
MHClip-B
MeerKAT: Meerkat Kalahari Audio Transcripts
animal2vec
KSounds
KC-Dialog
HateMM
ImpliHateVid
Human
Audiodatenklassifizierung und Sound Event Detection (SED) | SOTA | HyperAI