Speech-to-text
Converting spoken language in audio data into written text.
What is speech-to-text?
Speech-to-text, or STT, converts spoken language into text. Recording quality, pronunciation and surrounding noise can affect recognition. A live stream may first produce interim results that can still change. The transcript is a recognition result; the statement’s meaning and subsequent action need separate handling.
A fictional phone assistant processes “on Tuesday”. Even correct transcription does not establish a specific calendar date and time. The application must clarify them before creating an appointment. Unintelligible speech needs a suitable clarification question. The team therefore plans separate checks for recognised words, interpretation and actual appointment storage. Readable text alone is insufficient for that whole workflow.
Sources
Related terms
- Multimodal AIAI using several information types, such as text, images or sound, in inputs or outputs.
- Text-to-speechProducing synthetic spoken output from written text.
- AI chatbotAn AI chatbot supports dialogue using AI. A clear answer is not the same as a business operation actually completed.
- Data validationData validation checks data against defined requirements such as format, required fields or permitted value ranges.
- Model cardA model card documents an AI model’s purpose, foundations, evaluation conditions and known limitations for a particular version.
- AI readinessAI readiness concerns the foundations of an AI project: objectives, usable data, skills, responsibilities and an operating workflow.
Articles on this topic
AI & Automation with ASES
AI assistants and automated workflows