Voice Activity Detection

Voice activity detection identifies segments of audio that contain speech. It is useful for various applications in audio processing, including automatic speech recognition and speaker identification. The model is associated with tags such as pyannote, pyannote-audio, and voice-activity-detection. It has been trained on datasets like AMI, DiHard, and VoxConverse. The model is licensed under MIT. The collected information will help acquire a better knowledge of the pyannote.audio user base and assist maintainers in applying for grants to improve it further. Academic researchers are encouraged to cite relevant papers in their publications.