Audio Data Multiplexing for Real-Time Transcription

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing cellular-enabled devices struggle to capture and transcribe audio from communication sessions, particularly for hearing-impaired users, as audio from phone calls is often isolated from third-party applications and not easily multiplexed or transferred for real-time transcription.

Innovation Solution

A system that enables audio data from a cellular network to be received by a mobile device, multiplexed, and transmitted over a second wireless network to an audio output device, which then encodes and sends it to a transcription system for real-time transcription, allowing the user to receive a transcript on their device.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If audio data is transmitted over a second wireless network for transcription, then real-time transcription capability is improved, but device complexity increases due to support for multiple wireless network types

Engineering Contradiction:
Improvereal-time transcription capabilityVSAvoiddevice complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The mobile device is designed with multi-functionality to operate across multiple wireless network types (cellular and Wi-Fi). The device can dynamically switch between network types and simultaneously handle audio data transmission for both communication and transcription purposes, enabling real-time transcription without requiring separate dedicated devices for each function.

Inventive Principle:
Principle #6Universality (Multi-functionality)

2Measurement precision

If audio data is multiplexed and transmitted over a second wireless network, then transcription accuracy is improved, but loss of time increases due to additional encoding and transmission steps

Engineering Contradiction:
Improvetranscription accuracyVSAvoidtranscription delay
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The mobile device performs preliminary encoding of audio data into formats suitable for both cellular communication and Wi-Fi transmission before routing. By pre-processing the audio data and preparing multiple encoded versions in advance, the system avoids time-consuming real-time encoding during transmission, thus maintaining real-time transcription capability while ensuring high accuracy through proper encoding for the transcription system.

Inventive Principle:
Principle #10Preliminary action

3Adaptability or versatility

If the system supports multiple wireless network types for audio transmission, then adaptability is improved, but ease of operation deteriorates due to automatic network switching requirements

Engineering Contradiction:
Improvenetwork adaptabilityVSAvoidease of operation
Core Design Contradiction:
Adaptability or versatilityVSEase of operation

Solution Approach 1:

The system implements automatic network selection and switching mechanisms that operate without user intervention. The mobile device autonomously monitors available wireless networks, evaluates their suitability for audio transmission, and automatically switches between cellular and Wi-Fi networks based on signal quality, bandwidth availability, and power consumption considerations. This self-service approach maintains high network adaptability while preserving ease of operation for the end user.

Inventive Principle:
Principle #25Self-service

Data Source

PatentUS10834252B2Transcribing audio communication sessions
Publication Date: 2020.11.10 SORENSON IP HOLDINGS LLC
  • US10834252B2 patent drawing
  • US10834252B2 patent drawing
  • US10834252B2 patent drawing

AI summary

A computer-implemented method to provide transcriptions of an audio communication session is disclosed. The method may include receiving audio data at a first device from a second device over a first wireless network connection of a first wireless network type and providing the audio data to a speaker of the first device for output of the audio data. The method may further include encoding the audio data at the first device based on a second wireless network type and transmitting the encoded audio data from the first device over a second wireless network of the second wireless network type.