20240021204. SYSTEM AND METHOD FOR TRANSCRIPTION WORKFLOW simplified abstract (VIQ Solutions Inc.)

From WikiPatents
Jump to navigation Jump to search

SYSTEM AND METHOD FOR TRANSCRIPTION WORKFLOW

Organization Name

VIQ Solutions Inc.

Inventor(s)

Thomas Deplonty of Mississauga (CA)

Gilles-André Morin of Mississauga (CA)

SYSTEM AND METHOD FOR TRANSCRIPTION WORKFLOW - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240021204 titled 'SYSTEM AND METHOD FOR TRANSCRIPTION WORKFLOW

Simplified Explanation

The abstract describes a system, methods, and computer-readable storage media for assigning different speech-to-text engines based on previous transcription scores. The system can train a model using a first digital audio recording by randomly assigning speech-to-text engines to transcribe it and scoring the resulting transcriptions and the engines. A model is generated to select a speech-to-text engine from within the available engines. When a second digital audio recording is received, the model is executed to assign at least one selected speech-to-text engine to transcribe it.

  • The system trains a model using a first digital audio recording and scores the performance of different speech-to-text engines.
  • A model is generated to select the most suitable speech-to-text engine for transcription.
  • When a second digital audio recording is received, the model is used to assign the best speech-to-text engine for transcription.

Potential applications of this technology:

  • Transcription services: This technology can be used in transcription services to automatically assign the most accurate speech-to-text engine for transcribing audio recordings.
  • Voice assistants: Voice assistants can benefit from this technology by using the most suitable speech-to-text engine for accurately transcribing user commands.
  • Call center operations: Call centers can utilize this technology to improve the accuracy of transcriptions for customer interactions.

Problems solved by this technology:

  • Inaccurate transcriptions: By assigning the most suitable speech-to-text engine based on previous performance, this technology helps solve the problem of inaccurate transcriptions.
  • Time-consuming manual selection: Instead of manually selecting a speech-to-text engine for each audio recording, this technology automates the process, saving time and effort.

Benefits of this technology:

  • Improved transcription accuracy: By selecting the best speech-to-text engine, this technology improves the accuracy of transcriptions, leading to better understanding and analysis of audio recordings.
  • Efficiency and automation: The automated selection of speech-to-text engines streamlines the transcription process, making it more efficient and reducing the need for manual intervention.
  • Cost savings: With improved accuracy and efficiency, organizations can save costs associated with manual transcription or the use of less accurate speech-to-text engines.


Original Abstract Submitted

systems, methods, and computer-readable storage media for making assignments to different speech-to-text engines based on previous transcription scores. an exemplary system can train a model by receiving a first digital audio recording, randomly assigning speech-to-text engines to transcribe the first digital audio recording, and scoring the resulting transcriptions and scoring the engines based on their performances. the system can then generate a model for selecting a speech-to-text engine from within the speech-to-text engines. when a second digital audio recording is received, the system can assign, by executing the model, at least one selected speech-to-text engine from the speech-to-text engines to transcribe the second digital audio recording.