Speech and language processing#

ARI can recognize speech, handle dialogues, and synthesise voice in several languages. It is fully compliant with the ROS4HRI REP-155 ROS standard.

The entire speech pipeline runs on-board; no cloud-based services are used (and consequently, no Internet connection is required).

The following figure provides complete picture of the speech processing pipeline on ARI.

image/svg+xml external trigger on /chatbot/trigger chatbots definition reSpeaker audio /audio/channel0 /humans/voices/*/speech knowledge base ASR vosk language models 3D enviroment other knowledge Application controller /intents people perception (ROS4HRI) /look_at /tts/goal other actions touchcreen,motions & expresions chatbot RASA robot state web-based services queries queries queries

The main building blocks are:

General documentation#