Do you have interview data that needs to be transcribed for analysis? Griffith’s new speech-to-text service may be the answer.
The service simplifies audio transcription for Griffith researchers, while also increasing the security of the material transcribed. Audio and transcribed audio data aren’t shared with third parties, mined for information or stored in off-shore locations, which ensures a safer and more secure transcription service than third-party commercial options.
The new service uses Microsoft’s Azure transcription service to transcribe audio data. Machine learning models are used to automate this process, and transcriptions come with an impressive degree of accuracy. The service complies with Australian government, Griffith, and ARC funding requirements.
Examples of speech-to-text transcriptions can be found here, so you can see if the level of accuracy is suitable for your project. Tools and scripts for cleaning up the text transcription data are also available to further simplify the process.
The speech-to-text service is being offered and managed through Griffith’s eResearch Services. Fill in the online form to request an account, or visit the website to find out more about the service.
