AlexKly/Simple-Voice-Activity-Detector-using-MFCC-based-on-FPGA-Kintex
Voice Activity Detector based on MFCC features and DNN model
This project offers a Voice Activity Detector (VAD) implemented on an FPGA, which identifies segments of human speech within an audio signal. It takes raw audio data, processes it into features like MFCCs, and uses a trained neural network to classify if speech is present or absent. This is designed for engineers building smart home devices or other speech recognition systems who need real-time, hardware-accelerated speech detection.
No commits in the last 6 months.
Use this if you are developing a speech recognition system for smart home applications and need a hardware-accelerated solution for detecting the presence of human speech in real-time.
Not ideal if you are looking for a highly optimized, resource-efficient VAD solution or if you need to process analog microphone input directly without an external ADC.
Stars
29
Forks
4
Language
VHDL
License
—
Category
Last pushed
Jul 03, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/AlexKly/Simple-Voice-Activity-Detector-using-MFCC-based-on-FPGA-Kintex"
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
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。
flashlight/wav2letter
Facebook AI Research's Automatic Speech Recognition Toolkit
pannous/tensorflow-speech-recognition
🎙Speech recognition using the tensorflow deep learning framework, sequence-to-sequence neural networks