Guude! I’ve started a playlist where i explain terms from voice technology in 1 minute each. What do you think? Do you have any terms you’d like to see there?
2 Likes
Update - 15 phrases explained already on my “thorsten-voice” youtube channel 
.
What is … ? - Voice Technology terms explained: https://www.youtube.com/playlist?list=PL19C7uchWZep_xVxfz-_t1bbaf1G8AgsD
- speech technology
- stt (speech 2 text)
- wer (word error rate)
- rtf (real time factor)
- wakeword
- tts (text 2 speech)
- voice assistant
- nlu (natural language understanding)
- model
- dataset
- ai voice
- ssml (speech synthesis markup language)
- voice cloning / zero shot
- coqui tts
- piper tts
What do you think? Anything missing?
2 Likes
Looks like a good list to me! Some other ideas:
- neural network
- large language model
- RAG (Retrieval-Augmented Generation)
- Fine-tuning (not sure if this one has a precise definition)
- intent parsing