What is automatic speech recognition (ASR)?
The field of technology that recognises spoken words and converts them into text.
Automatic speech recognition (ASR), explained
ASR is the engine behind speech-to-text. Modern ASR uses neural networks trained on large amounts of recorded speech.
Telephone audio is harder than studio audio because it is compressed to a narrow band, so ASR for phone calls needs models that handle low-quality audio well.
See how these ideas come together in Chitti, Manolle's AI voice agent.
Related terms
- Speech-to-text (STT)Technology that converts spoken audio into written text, also called automatic speech recognition (ASR).
- PSTN (public switched telephone network)The worldwide network of ordinary phone lines and mobile networks that phone calls travel over.
- Latency (voice response time)The delay between the caller finishing speaking and hearing the agent's reply.
See an AI voice agent at work on your calls.
See the complete system live: marketing, lead capture, AI voice calling, sales conversion, and analytics.