Liulishuo Tech Team
Sep 3, 2016 · Artificial Intelligence
Optimizing Deep Neural Network Inference for Offline Speech Evaluation on Mobile Devices
This article describes how the English fluency app leverages deep neural network (DNN) models for real‑time speech scoring on smartphones, detailing offline inference challenges, BLAS‑based matrix‑vector optimizations, sparsity exploitation, cache‑friendly implementations, fixed‑point and NEON acceleration, as well as model compression techniques to improve accuracy and latency.
BLASDNN optimizationdeep learning
0 likes · 11 min read