Overview
ISO/IEC 20382-1:2017 - "Information technology - User interfaces - Face-to-face speech translation - Part 1: User interface" defines a standardized framework for face-to-face speech translation user interfaces. The standard specifies features, general requirements and functionality to enable interoperable speech-translation sessions among multiple systems and languages in close-range, in-person situations. It applies to user interfaces and communication protocols for session setup, but does not define the speech translation engine itself.
Key topics and technical requirements
- Scope & purpose: Support convenient, interoperable face-to-face speech translation using mobile and wearable devices while reflecting user characteristics (speech style, emotion, etc.).
- Service flow: Defines typical steps - local speech capture, on-device speech recognition, translation request to a translation server, return of translated text, short-range wireless communication (SRWC) to peer device, and speech synthesis (TTS) output.
- Service types: Two-way (two participants) and multi-way (three or more participants).
- Service modes: Open, Protected (privacy-controlled), Automatic, and Manual - to suit public vs. private and automatic vs. user-controlled scenarios.
- Functional requirements:
- User communication: Minimal steps to start a session (e.g., start with fewer than 3 operations).
- User interface: Requirements for setup, correction/selection of recognition results, and representation of translated messages.
- User device: Roles for mobile devices and wearable devices (microphone/speaker), SRWC pairing, and message exchange.
- Accessibility: Multi-modal input/output, voice input/output, simple/controlled language support and other accessibility features.
- Functional components & protocols: Defines protocol interactions among components, session connection/disconnection sequences, end conditions, and device-level functions (pairing, wearable control).
- Terminology: Key terms include SRWC (short range wireless communication), F2F (face-to-face), TTS, AI/VI indicators, MD (mobile device), WD (wearable device).
Applications and practical value
ISO/IEC 20382-1 is practical for:
- Real-time multilingual communication in tourism, healthcare, customer service, emergency response, and business meetings.
- Designing mobile and wearable translation apps that must interoperate across vendors and languages.
- Implementing privacy modes and accessibility features for inclusive face-to-face interactions.
Who should use this standard
- UI/UX designers and product managers for speech-translation apps
- System architects and developers integrating ASR/TTS with translation servers
- Wearable and mobile device manufacturers
- Service providers offering on-site multilingual communication solutions
- Accessibility specialists ensuring inclusive speech-translation interfaces
Related standards
- ISO/IEC 20382-2:2017 - Information technology - User interface - Face-to-face speech translation - Part 2: System architecture and functional components (normative reference for architecture and component details).