Multi-speaker separation, identification, diarization ALL-IN-ONE. It can isolate the target speaker from a conversation audio and do ASR.
Implementation of "SpEx: Multi-Scale Time Domain Speaker Extraction Network".
This is a demo for my bachelor thesis 'Speaker Separation and Machine Auditory Perception for Dialogue Scene'.
ONNX implementation of Pyannote Speaker Diarization Community-1 pipeline.
Quantization Aware Training (QAT) of Conv-TasNet speech separation model
Transcripción de reuniones en español con separación de hablantes sin diarización: micrófono y loopback del sistema como canales independientes. faster-whisper, todo local.
Stream Server for connecting Twilio's Media Stream to Symbl over a WebSocket with an exposed RESTful API for triggering the delivery of Symbl’s real-time events to a Client server.
AI-powered voice separation tool that analyzes YouTube videos and automatically groups speech by character
🎙️ Identify and extract target speaker's speech from multi-speaker audio using deep learning, enhancing clarity in complex conversations.
To associate your repository with the speaker-separation topic, visit your repo's landing page and select "manage topics."