filippogiruzzi/voice_activity_detection
Voice Activity Detection based on Deep Learning & TensorFlow
Implements a 1D ResNet CNN architecture that processes MFCC-extracted audio features to classify speech versus noise signals, achieving 97% test accuracy. Supports end-to-end workflows including automatic dataset labeling, TFRecord-based data pipeline, model training, and inference with temporal smoothing post-processing. Available as a Docker container for reproducible deployment with GPU acceleration.
371 stars. No commits in the last 6 months.
Stars
371
Forks
69
Language
Python
License
GPL-3.0
Category
Last pushed
Mar 24, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/filippogiruzzi/voice_activity_detection"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
espnet/espnet
End-to-End Speech Processing Toolkit
yeyupiaoling/PPASR
基于PaddlePaddle实现端到端中文语音识别，从入门到实战，超简单的入门案例，超实用的企业项目。支持当前最流行的DeepSpeech2、Conformer、Squeezeformer模型
flashlight/wav2letter
Facebook AI Research's Automatic Speech Recognition Toolkit
yeyupiaoling/PaddlePaddle-DeepSpeech
基于PaddlePaddle实现的语音识别，中文语音识别。项目完善，识别效果好。支持Windows，Linux下训练和预测，支持Nvidia Jetson开发板预测。
philipperemy/deep-speaker
Deep Speaker: an End-to-End Neural Speaker Embedding System.