ACM MM 2021: 'Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual Active Speaker Detection'
-
Updated
Oct 23, 2023 - Python
#
active-speaker-detection
Here are 13 public repositories matching this topic...
Learning Long-Term Spatial-Temporal Graphs for Active Speaker Detection (ECCV 2022)
-
Updated
Oct 29, 2023 - Python
AnnoTheia is a data annotation toolkit that identifies when a person speaks in a scene and transcribes their speech, also offering flexibility to replace modules for different languages.
-
Updated
Jul 26, 2024 - Python
Accepted by TMM 2022
-
Updated
Aug 18, 2022 - Python
Open-source Opus Clip alternative. Turn long videos into vertical clips with AI-picked moments, virality scoring, animated captions, auto zoom and speaker-aware reframing. Free desktop app for macOS, Windows and Linux.
electron desktop-app typescript ffmpeg cross-platform captions subtitles openai video-editing whisper video-editor tiktok content-creation open-source-alternative active-speaker-detection reels youtube-shorts ai-video short-form-video auto-reframe
-
Updated
Aug 3, 2026 - TypeScript
Active speaker detection: two-stream audio-visual CNN for AVA Active Speaker format data, with a live in-browser demo
-
Updated
Jul 28, 2026 - Python
Turns long podcasts and interviews into vertical short clips. WhisperX transcription, Gemini picks the moments, active speaker detection reframes to 9:16 with burned-in captions.
-
Updated
Aug 2, 2026 - TypeScript
SyncNet based on Meta's Perception Encoder Audio-Visual (PE-AV)
pytorch lip-sync lipsync time-synchronization multimodal-learning audio-visual lip active-speaker-detection time-delay-estimation syncnet lip-sync-detection audio-visual-sync
-
Updated
Jul 28, 2026 - Python
Audio-visual synchronization and active-speaker detection in Python via cross-modal correlation
-
Updated
Jul 31, 2026 - Python
RNN-based Active Speaker Detection from facial landmarks (UniTalk-ASD + AVA + WASD)
machine-learning computer-vision deep-learning pytorch lstm rnn video-understanding face-landmarks mediapipe active-speaker-detection
-
Updated
Jul 29, 2026 - Jupyter Notebook
Click a person in a video and listen to their voice.
-
Updated
Aug 5, 2026 - Python
视听多模态目标说话人增强：Light-ASD 身份先验、SRP-PHAT 与八通道 SBL-INCM-MVDR 波束形成
opencv pytorch audio-signal-processing beamforming microphone-array multimodal-learning doa-estimation array-signal-processing mvdr active-speaker-detection
-
Updated
Jul 29, 2026 - Python
Proactive AI for smart glasses
-
Updated
May 25, 2026 - Python
Improve this page
Add a description, image, and links to the active-speaker-detection topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the active-speaker-detection topic, visit your repo's landing page and select "manage topics."