meshaun9 / openvino_speech_recognition

This project is a speech recognition demo that uses OpenVINO, a TensorFlow Speech Recognition model, and can be deployed on Intel's CPU, GPU, and NCS2.

OpenVINO Speech Recognition Demo for NeurIPS 2018

This is a speech recognization demo that uses OpenVINO for inference, uses TensorFlow Speech Recognition model, and can be deployed on Intel's CPU, GPU, and NCS2. Based on the inference results the robotic arm will attempt sign language and hand gestures.

System Configuration

Software

• Intel(R) Distribution of OpenVINO(TM) Toolkit
• Install mraa
• Install TensorFlow 1.5

Note: Later versions of Tensorflow require AVX instruction set which isn't supported by the Up-board.

Hardware

• Up-board
• 5-DOF Humanoid Robotic Arm and Hand
• AdaFruit 16-channel 12-bit PWM/Servo Shield - I2C interface