Espressif ESP-SR helps users build AI speech solutions based on ESP32-S3 or ESP32-P4 chips.
ESP-SR framework includes the following modules:
These algorithms are provided in the form of a component, so they can be integrated into your projects with minimum effort.
ESP32-S3/ESP32-P4 are recommended, which support AI instructions and larger, high-speed octal SPI PSRAM. The new algorithms will no longer support ESP32 chips.
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 listen to wake words, such as Alexa, Hi,lexin and Hi,ESP.
Espressif offers two ways to customize the wake word, please refer to the following document to choose the one that meets your needs: Espressif Speech Wake Words Customization Process or Training Wake Words by TTS sample.
The following wake words are supported in esp-sr:
wake words | ESP32 | ESP32-S3/ESP32-P4 |
---|---|---|
Hi, | wn5_hilexin, wn5_hilexinX3 | wn9_hilexin |
wn5_nihaoxiaozhi,wn5_nihaoxiaozhiX3 | wn9_nihaoxiaozhi_tts | |
wn9_xiaoaitongxue | ||
Hi,ESP | wn9_hiesp | |
Hi,M Five | wn9_himfive | |
Alexa | wn9_alexa | |
Jarvis | wn9_jarvis_tts | |
Computer | wn9_computer_tts | |
Hey,Willow | wn9_heywillow_tts | |
Sophia | wn9_sophia_tts | |
Mycroft | wn9_mycroft_tts | |
Hey,Printer | wn9_heyprinter_tts | |
Hi,Joy | wn9_hijoy_tts | |
Hey,Wand | wn9_heywanda_tts | |
Astrolabe | wn9_astrolabe_tts | |
wn9_nihaoxiaoxin_tts | ||
wn9_xiaomeitongxue_tts | ||
Hi, | wn9_hixiaoxing_tts | |
wn9_xiaolongxiaolong_tts | ||
wn9_miaomiaotongxue_tts | ||
Hi, | wn9_himiaomiao_tts | |
Hi,Lily/Hi, | wn9_hilili_tts | |
Hi,Telly/Hi, | wn9_hitelly_tts | |
/ | wn9_xiaobinxiaobin_tts |
NOTE: _tts
suffix means this WakeNet model is trained by TTS samples.
Espressif's speech command recognition model MultiNet is specially designed to provide a flexible off-line 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 300 Chinese or English speech commands, such as (Turn on the air conditioner) and (Turn on the bedroom light).
The following MultiNet models are supported in esp-sr:
language | ESP32 | ESP32-S3 | ESP32-P4 |
---|---|---|---|
Chinese | mn2_cn | mn5q8_cn, mn6_cn, mn7_cn | mn7_cn |
English | mn5q8_en, mn6_en, mn7_en | mn7_en |
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.
In order to achieve optimal performance: