Overview
ISO/IEC 23773-1:2024 defines the general description and user-interface context for real-time automatic simultaneous interpretation systems that interoperate among natural languages for spontaneous speech. It clarifies scope, terminology (e.g., interpretation unit, incremental knowledge learning), typical service flows and use-case situations (live lectures, video calls, meetings, phone calls, chat), and the high-level functional components needed to deliver continuous, in‑flight interpretation. This part is a general, non‑normative foundation; detailed UI requirements and system architecture are covered in Parts 2 and 3 of the series.
Key topics and technical focus
- Service situations and scenarios: classification of UIs by context - public speeches, bi-directional video talks, multi‑party meetings, phone calls, and text/chat scenarios.
- Service flow: typical real‑time process from speech input → continuous speech recognition → machine translation (server) → text output → optional TTS for audio output.
- Functional components:
- Simultaneous interpretation application (top‑level UI layer)
- Continuous speech recognition (real‑time ASR)
- Interpretation unit extraction (segmenting speech into units for interpretation)
- Real‑time simultaneous interpretation (incremental translation while speaking)
- Incremental knowledge learning (building speech/translation/user/domain knowledge databases)
- Presentation of translation results (text, speech, gestures; presentation control)
- Deployment modes: components (ASR, TTS, translation server) may operate locally or remotely depending on device and service type.
- Exclusions: this document does not cover sign language interpretation.
Applications and practical value
ISO/IEC 23773-1 is applicable to designers and implementers of real‑time multilingual communication solutions where low latency and continuous interpretation are required:
- Live lecture translation, conference and event interpretation
- Video conferencing and remote meetings with multilingual participants
- Phone-based bilingual communication services
- Travel and wearable translator devices for on‑the‑go conversation
- Multilingual chatbots and text‑based interpreting services
Benefits include consistent UI expectations across platforms, clearer integration points for ASR/MT/TTS, and guidance for incremental learning to improve domain and user personalization.
Who should use this standard
- UI/UX designers and product managers for interpretation systems
- System architects and software developers of ASR/MT/TTS services
- Vendors of wearable translators, conferencing platforms, and telephony interpreters
- Event organizers, accessibility coordinators, and localization teams
- Standards and compliance officers planning interoperable interpretation services
Related standards
Keywords: ISO/IEC 23773-1, automatic simultaneous interpretation, real-time interpretation, user interface, continuous speech recognition, interpretation unit, incremental knowledge learning, TTS, machine translation.