SOTAVerified

Activity Detection

Detecting activities in extended videos.

Papers

Showing 110 of 380 papers

TitleStatusHype
Moshi: a speech-text foundation model for real-time dialogueCode9
pyannote.audio: neural building blocks for speaker diarizationCode3
audino: A Modern Annotation Tool for Audio and SpeechCode2
Speaker Diarization with Overlapping Community Detection Using Graph Attention Networks and Label Propagation AlgorithmCode1
VANPY: Voice Analysis FrameworkCode1
WiFi CSI Based Temporal Activity Detection via Dual Pyramid NetworkCode1
InaGVAD : a Challenging French TV and Radio Corpus Annotated for Speech Activity Detection and Speaker Gender SegmentationCode1
Online speaker diarization of meetings guided by speech separationCode1
ivrit.ai: A Comprehensive Dataset of Hebrew Speech for AI Research and DevelopmentCode1
TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker EmbeddingsCode1
Show:102550
← PrevPage 1 of 38Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CNN-BiLSTM_bestROC-AUC95.14Unverified
2CNN-BiLSTM_smallROC-AUC95.13Unverified
3SG-VAD (ours)ROC-AUC94.3Unverified
4ADA-VADROC-AUC79.1Unverified