Overview
ISO/IEC 23773-2:2024 is a key international standard specifying the user interface (UI) requirements and functional description for real-time automatic simultaneous interpretation systems. These systems are designed to facilitate communication across different natural languages during spontaneous speech, enabling near-instantaneous translation akin to simultaneous interpretation.
Unlike traditional speech-to-speech translation systems that focus on consecutive interpretation, this standard targets the unique challenges of simultaneous interpretation, emphasizing continuous, real-time translation. The document excludes sign language interpretation.
This standard is part of the broader ISO/IEC 23773 series focused on automatic simultaneous interpretation technology, ensuring interoperability and usability across different platforms and languages.
Key Topics
-
User Interface Requirements:
- Input can be in text or speech form; output is produced in the target language as text or spoken speech.
- Support for continuous, automatic simultaneous interpretation of user input without delay.
- Optional features include multi-user sessions, adding participants dynamically, source and target language selection, and user preference settings.
- Translation results should ideally be delivered within 3 seconds after a user’s utterance ends.
- Speech output may reflect speaker characteristics such as gender, pitch, power, and emotion.
-
User Device Requirements:
- Devices must support both input and output functions suitable for simultaneous interpretation.
- Optional ease-of-use features include confirmation signals for session participation and quick operation initiation within 3 minutes.
-
Accessibility Requirements:
- Essential accessibility functions include allowing input and output in both text and speech form.
- Optional features include multi-modal interfaces (text, touch, gesture) and user preference settings tailored for accessibility.
- Support for providing translation results in controlled language to improve comprehension, enhancing usability for people with specific needs.
-
Functional UI Components:
- Setup Function: Enables users to start interpretation sessions, select languages, and configure output preferences (speech, text, or both).
- Input/Output Function: Manages real-time speech and text input as well as translation output, linking to core system modules like speech recognition and translation engines.
- Correction/Selection Function: Allows users to correct errors in recognition or interpretation through keyboard, gesture, or voice commands. While primarily for system improvement and testing, this feedback loop enhances ongoing accuracy.
- Accessibility Features: Provide multi-modal input/output capabilities to support users with disabilities, enhancing inclusivity in international communication.
Applications
ISO/IEC 23773-2:2024 is crucial for developers, vendors, and users of automatic simultaneous interpretation systems deployed in:
- Multilingual video conferencing and calls: Facilitating seamless communication during global meetings.
- Live translation for lectures and seminars: Enabling real-time understanding for international audiences.
- Wearable translation devices: Providing on-the-go, real-time interpretation for travelers and field workers.
- Global event management: Supporting multilingual interactions during conferences, trade fairs, and forums.
- Telecommunication services: Enhancing customer support and communication across language barriers.
This standard helps ensure that UIs for these systems are consistent, user-friendly, and accessible, meeting international expectations for functionality, responsiveness, and inclusivity.
Related Standards
- ISO/IEC 23773-1: General description of automatic simultaneous interpretation systems, offering foundational definitions and concepts.
- ISO/IEC 23773-3: Reference architecture outlining high-level functional modules and communication interfaces critical to simultaneous interpretation systems.
- ISO/TS 24620-1: Provides definitions and guidelines for controlled languages, which ISO/IEC 23773-2 suggests using to improve translation clarity and accessibility.
Conclusion
ISO/IEC 23773-2:2024 establishes comprehensive UI requirements and functional descriptions for automatic simultaneous interpretation systems, focusing on real-time, multi-language, spontaneous speech translation. By addressing user interface design, device capabilities, and accessibility considerations, this standard supports the development of effective, inclusive, and interoperable interpretation solutions that meet the increasing global demand for instantaneous multilingual communication.