speech-detection

Automagically synchronize subtitles with video.

CNN-based audio segmentation toolkit. Allows to detect speech, music, noise and speaker gender. Has been designed for large scale gender equality studies based on speech time per gender.

Voice Activity Detection based on Deep Learning & TensorFlow

Synchronize your subtitles using machine learning

EduSense: Practical Classroom Sensing at Scale

Visual only speech detection by lip movement. There are countless situations where you can't hear the audio, and it's really frustrating.

CLI Python basata su AI per rimuovere automaticamente silenzi e segmenti senza parlato dai video, utilizzando Silero VAD e FFmpeg.

Smart human voice recorder using Silero VAD (PyTorch) + frequency analysis — detects & records speech while filtering background noise. Auto-stops on silence with configurable thresholds.

Causal, real-time answering-machine detection from live call audio — predicts human vs. machine at 250ms checkpoints under a strict false-hangup budget. CPU-only, no pretrained models.

A simple, mobile, friendly command detection model

A Python-based system for automatic word segmentation in speech using ML models like SVM, MLP, and RNN.

A non-destructive video moment editor with smart audio segmentation and professional clip export.

`inaSpeechSegmenter` web UI.