Speech Recognition for Rail Communication Documentation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for documenting voice-based communication in rail operations are inefficient and prone to errors due to manual transcription and confirmation processes, especially in noisy environments and critical situations where reliability and speed are crucial.

Innovation Solution

A method utilizing speech recognition devices for automatic digitization and verification of voice messages and confirmations, ensuring secure and reliable communication through a transaction-based system, which can operate independently and reduce human error.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual transcription and confirmation processes are used for documenting voice-based communication, then the process allows human verification and understanding, but the process becomes time-consuming and error-prone

Engineering Contradiction:
Improvedocumentation accuracyVSAvoiddocumentation time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent replaces the mechanical manual transcription process with automatic speech recognition technology. The speech recognition device automatically transcribes voice messages and confirmations into text form, eliminating the need for manual writing and significantly reducing documentation time while maintaining accuracy through automated verification processes.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service documentation where the speech recognition device automatically documents both the original message and the confirmation without requiring human intervention for transcription. The automated system handles the entire documentation process, from capturing the voice message to verifying the confirmation, thereby eliminating time loss associated with manual processes.

Inventive Principle:
Principle #25Self-service

2Productivity

If automatic speech recognition is used for digitizing voice radio, then the documentation process becomes faster and more efficient, but the system becomes more complex

Engineering Contradiction:
Improvedocumentation efficiencyVSAvoidsystem complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The speech recognition device is designed to perform multiple functions: it captures voice messages, transcribes them into text, stores the documentation, and verifies confirmations. By consolidating these functions into a single multi-functional device, the system achieves high productivity without proportionally increasing overall system complexity.

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

Solution Approach 2:

The patent introduces a communication channel that serves as an intermediary between the sender and receiver, facilitating the transmission of both voice messages and their text transcriptions. This intermediary channel manages the complexity by providing a standardized interface for data exchange, allowing the speech recognition system to operate efficiently without overwhelming system complexity.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Reliability

If manual confirmation processes are used, then the communication can be verified by the recipient, but the confirmation process becomes time-consuming and error-prone

Engineering Contradiction:
Improvecommunication verificationVSAvoidconfirmation speed
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The patent replaces manual confirmation processes with automatic speech recognition technology. The recipient's confirmation is captured through speech recognition and automatically transcribed and verified, eliminating the time-consuming nature of manual confirmation while maintaining reliability through automated verification mechanisms.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system implements an automated feedback mechanism where the recipient's confirmation is immediately captured, transcribed, and transmitted back to the sender. This feedback loop occurs automatically and rapidly, significantly increasing confirmation speed while maintaining verification reliability through the automated speech recognition and comparison processes.

Inventive Principle:
Principle #23Feedback

4Ease of operation

If voice communication is used in noisy environments, then the communication channel remains simple and accessible, but the voice recognition accuracy deteriorates

Engineering Contradiction:
Improvecommunication accessibilityVSAvoidspeech recognition accuracy
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The patent introduces a communication channel as an intermediary that facilitates the transmission of voice messages between sender and receiver. This channel serves as a buffer that allows voice communication to occur in noisy environments while maintaining ease of operation, as the channel handles the transmission complexities.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system replaces manual verification of voice messages with automatic speech recognition technology. The speech recognition device automatically processes and transcribes voice messages even in noisy environments, maintaining measurement precision through automated algorithms that can filter and interpret speech patterns despite background noise, thereby preserving both accessibility and accuracy.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentEP3871944A1Method for documentation of a voice-based communication
Publication Date: 2021.09.01 SIEMENS MOBILITY GMBH
  • EP3871944A1 patent drawingFigure 1~2
  • EP3871944A1 patent drawingFigure 3~4
  • EP3871944A1 patent drawingFigure 5

AI summary

In one embodiment, the method serves to document speech-based communication and comprises the steps of: - providing a sender-side and/or receiver-side speech recognition device (4), - speaking and transmitting a message (M) via a communication channel (3) from a sender (A) to a receiver (B) and sender-side and/or receiver-side digitization and storage of the message (M) using the speech recognition device (4), and - speaking an acknowledgment (C) of the message (M) by the receiver (B) and sender-side and/or receiver-side digitization and storage of the acknowledgment (C) using the speech recognition device (4).