Skip to content

Latest commit

 

History

History
95 lines (56 loc) · 7.79 KB

README.md

File metadata and controls

95 lines (56 loc) · 7.79 KB
Raw

ESP-Skainet [中文]

ESP-Skainet is Espressif's intelligent voice assistant, which currently supports the Wake Word Engine and Speech Commands Recognition.

ESP32-S3 is recommend to run speech commands recognition, which supports AI instructions and high-speed octal SPI PSRAM. The Latest models will be deployed on ESP32-S3 first.

Overview

ESP-Skainet supports the development of wake word detection and speech commands recognition applications based around Espressif Systems' ESP32 series chip in the most convenient way. With ESP-Skainet, you can easily build up wake word detection and speech command recognition applications.

In general, the ESP-Skainet features will be supported, as shown below:

overview

Input Voice Stream

The input audio stream can come from any way of providing voice, such as MIC, wav/pcm files in flash/SD Card.

Wake Word Engine

Espressif wake word engine WakeNet is specially designed to provide a high performance and low memory footprint wake word detection algorithm for users, which enables devices always wait for wake words, such as "Alexa", “天猫精灵” (Tian Mao Jing Ling), and “小爱同学” (Xiao Ai Tong Xue).

Currently, Espressif has not only provided an official wake word "Hi, Lexin" to the public for free but also allows customized wake words. For details on how to customize your own wake words, please see Espressif Speech Wake Words Customization Process.

Speech Commands Recognition

Espressif's speech command recognition model MultiNet is specially designed to provide a flexible offline speech command recognition model. With this model, you can easily add your own speech commands, eliminating the need to train model again.

Currently, Espressif MultiNet supports up to 200 Chinese or English speech commands, such as “打开空调” (Turn on the air conditioner) and “打开卧室灯” (Turn on the bedroom light).

Audio Front End

Espressif Audio Front-End AFE integrates AEC (Acoustic Echo Cancellation), VAD (Voice Activity Detection),BSS (Blind Source Separation) and NS (Noise Suppression).

Our two-mic Audio Front-End (AFE) have been qualified as a “Software Audio Front-End Solution” for Amazon Alexa Built-in devices. afe

Quick Start with ESP-Skainet

Hardware Preparation

To run ESP-Skainet, you need to have an ESP32 or ESP32-S3 development board which integrates an audio input module . Development board Support:

Example Name Latest Models Supported Board
cn_speech_commands_recognition MultiNet7 ESP32-Korvo, ESP32-S3-Korvo-1, ESP-BOX, ESP-S3-Korvo-2, ESP32-S3-EYE, ESP32-P4-Function-EV
en_speech_commands_recognition MultiNet7 ESP32-S3-Korvo-1, ESP-BOX, ESP-S3-Korvo-2, ESP32-S3-EYE, ESP32-P4-Function-EV
wake_word_detection Wakenet9 ESP32-Korvo, ESP32-S3-Korvo-1, ESP-BOX, ESP-S3-Korvo-2, ESP32-S3-EYE, ESP32-P4-Function-EV
chinese_tts esp-tts-v1.7 ESP32-Korvo, ESP32-S3-Korvo-1, ESP-BOX, ESP-S3-Korvo-2, ESP32-P4-Function-EV
usb_mic_recorder ESP-BOX, ESP-S3-Korvo-2

On how to configure your applications, please refer to the README.md of each example.

Software Preparation

ESP-Skainet

Clone this project as follows:

git clone https://github.com/espressif/esp-skainet.git

ESP-IDF

ESP-IDF v4.4 and ESP-IDF v5.0 are supported. If you had already configured ESP-IDF before, and do not want to change your existing one, you can configure the IDF_PATH environment variable to the path to ESP-IDF.

For details on how to set up the ESP-IDF, please refer to Getting Started Guide for ESP-IDF release/v4.4 branch

Examples

The folder of examples contains some applications demonstrating the API features of ESP-Skainet.

Please start with the wake_word_detection example.

  1. Navigate to one example folder `esp-skainet/examples/wake_word_detection).
cd esp-skainet/examples/wake_word_detection
  1. Compile and flash the project.
idf.py flash monitor
  1. Advanced users can add or modify speech commands by using the idf.py menuconfig command.

For details, please read the README file in each example.

Resources