Transcription with Speech-to-Text Programs

In Communication and IT at the advanced level, students are required to conduct various interviews throughout their education. They need to be familiar with data collection methods and how to process what they have collected afterward.

Transcribing interviews is one of the most tedious parts of the process, as students must listen to the recordings repeatedly, check for keywords and phrases, and then write down what they have heard. Sometimes, this process can take a lot of time, especially if they have a lot of material to organize. Therefore, we have worked on having the computer perform speech-to-text, which can save much time in teaching.

Why should you use speech recognition software?

You should use speech recognition software for several reasons. Firstly, it can make your life much easier, as instead of typing everything you hear, you can speak. And because it's an automated process, you can add more material to your archive without worrying about remembering what you have already heard.

Below are two programs that can be used in education.

Microsoft Dictate

Microsoft has released a plugin for the Office suite that can convert speech to text. It's free to use but requires a Windows computer. It uses the same speech recognition technology as the Cortana Virtual Assistant and is on the same level as paid versions.

Once installed, you can access it via the "Dictation" tab at the top of the toolbar - Word, PowerPoint, and Outlook.

Price: Free

Google Docs Voice Typing

Google Docs already has built-in technology and dictation tools.
To use voice typing with Google Docs, you click on the "Tools" button, select "Voice typing," and then give Google access to the microphone on your laptop or PC.

Compatibility: Any Google Chrome-compatible device

Price: Free

Which one should you use?

It depends on your needs. If you are new to transcription and don't need a lot of advanced tools, Google Docs or Microsoft Dictate are good options.

But... we can also use AI, which opens up a whole new set of possibilities.

NLP Cloud systems are designed to work with different types of audio and video content and can also automatically correct spelling errors and improve the audio quality of transcriptions. At the same time, they can summarize the content of an interview, who is speaking, and what topics are the most important.

NLP Cloud is not free, but you can create a user and test their examples here. If you want your audio file transcribed, you must pay 1 dollar per month upfront, and there is a small fee each time you submit files.

NLP Cloud transcription can be tried at this address:https://nlpcloud.com/home/playground/asr

A summary of the transcription can be made via this page:
https://nlpcloud.com/home/playground/dialogue-summarization