Xianyu Technology
Apr 20, 2018 · Artificial Intelligence
Client‑Side Voice Recognition with TensorFlow Lite and MFCC Optimization
The paper presents a client‑side speech recognizer that uses a compact TensorFlow Lite Inception‑v3 CNN model combined with an optimized MFCC feature pipeline and ARM‑NEON‑accelerated, multi‑threaded processing, achieving low‑latency, high‑accuracy voice recognition on mobile and embedded devices.
MFCCNeural networksTensorFlow Lite
0 likes · 14 min read