Telecommunications Relay Language Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional telecommunications relay systems for hearing-impaired individuals face delays and inefficiencies when dealing with multiple languages, requiring intervention from users to change call agents and resulting in latency issues that affect the user experience.
Innovation Solution
A telecommunications relay system using automatic speech recognition to identify and transcribe spoken languages in real-time, managing multiple ASR groups to minimize latency and automate language detection, ensuring seamless communication without user intervention.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If multiple call agents are switched to handle different languages, then language coverage is improved, but call latency increases and user experience deteriorates
Solution Approach 1:
The system performs preliminary language detection and ASR group selection before the call begins. The call serving entity detects the language of the incoming call and proactively selects the appropriate ASR group, eliminating the need for post-detection switching and reducing latency.
Solution Approach 2:
The call serving entity acts as an intermediary that manages language detection and ASR group selection. It receives the incoming call, detects the language, selects the appropriate ASR group, and establishes the voice path, thereby mediating between the peer and the hearing-impaired user to minimize latency.
2Measurement precision
If user intervention is required to change call agents, then language accuracy is improved, but ease of operation deteriorates
Solution Approach 1:
The system performs self-service by automatically detecting the language and selecting the appropriate ASR group without requiring user intervention. The call serving entity independently handles language detection and call agent selection, making the system autonomous and improving ease of operation.
3Measurement precision
If conventional TRS transcribes voice to text with minimum round trip delay of 300 ms, then transcription accuracy is maintained, but speed deteriorates
Solution Approach 1:
The system establishes the voice path and selects the ASR group before the actual transcription begins. This preliminary setup allows the transcription process to start immediately without waiting for user intervention or call agent switching, reducing the round trip delay and increasing speed.
Data Source
AI summary
A system for identifying spoken language in a telecommunications relay service, which includes a call serving entity; and a plurality of automatic speech recognition groups where each of the automatic speech recognition groups includes an associated automatic speech recognition engine that recognizes and transcribes speech to a predefined language. One of the plurality of automatic speech recognition groups is set as a default automatic speech recognition group and automatic speech recognition engines transcribe and convert peer voices into text packets. The text packets are scored by the automatic speech recognition engine and transmitted to the call serving entity to determine whether the text packets meet a predetermined threshold based on their respective scores with the text packet having the highest score that meets or exceeds the predetermine threshold transmitted to a user.