Speech-to-Text service
eResearch services has developed the speech-to-text service that automatically transcribes audio data. This service is safe, secure and complies with Australian government, Griffith, and ARC funding requirements.
The speech-to-text service uses the Microsoft Azure transcription service to transcribe your audio data. Machine learning models are used to automate this process, this is where Microsoft's wealth of training data comes in handy to create transcriptions with a high accuracy.
Unlike other transcription services, the speech-to-text service is secure. That is, your data will not be shared with third parties, mined for information, or stored in an off-shore location.
Accessing Speech-to-Text
Griffith University members are able to log in directly without approval or account setup. The service is available at:
Speech-to-Text Transcription Service@Griffith
The Griffith VPN is required to use the Speech-to-Text Service.
You can log in using your Griffith credentials.
Once you successfully log in, there is a help file located on the front page, this is found by clicking the circled "i" symbol (for information) on the top right of the page.
If you experience any issues with this service, please fill in this form.
Note that any uploaded audio files and associated transcription older than 30 days will be automatically removed from the system. Since the system is not designed as a data repository, it is recommended that once you've completed the transcription of your uploaded audio, download the transcription and store your audio and transcription files on either SharePoint or Research Drive. Check out available research storage options.
Access to the application is only available to Griffith University members. If you would like to add someone external to Griffith, you will need to fill out this form to arrange a Griffith visitors account.
Resources
- Useful booklet regarding audio-visual recording in human research.
- This User Document (also available on the Speech-to-Text Service) will help you get started and is helpful for troubleshooting transcription errors.