The online speech-to-text application Beey has launched a new generation of automatic recognition software. As expected, it performs more accurately and reliably than the previous model. Moreover, it has even passed in contrast to the global competition. See how Beey’s transcription of various recordings compares to the results of Microsoft and Google’s recognition programs.
Our team of professional editors uses the Beey online editor to speed up and streamline the creation of high-quality transcripts and subtitles for recordings in Czech and Ukrainian languages. This process can be also used by TV stations and government institutions to help during the current situation in Europe.
Have you ever wondered how speech-to-text conversion actually works? Beey’s system is based on the technology developed at the Technical University of Liberec, one of our long time partners. The founder and original team leader of the Computer Speech Processing Laboratory (SpeechLab), prof. Ing. Jan Nouza, CSc., has given an interview to the news service iDNES.cz, in which he describes their system for automatic voice recognition in more detail. You can read an excerpt of this article, where the professor explains his part of the process, below.
Beey’s users are well-represented in the journalism industry. One of them, Radka Wallerová, works as editor at Seznam zprávy and regularly uses Beey to transcribe interviews. She has been working as a journalist for many years. She told us about the first time she met our current president and what he was drinking at the time, how journalism has changed over the years, and what aspects of her job she doesn’t enjoy.
We are constantly striving to improve Beey so that the resulting transcripts are as accurate as possible, and so that our users can save as much time as possible during the subsequent editing. It is important that Beey can recognize all the words that appear in the recordings, which is why every morning we perform a dictionary update, adding new words from the previous day.
Equally important, however, is having a good quality recording as the input, and this is something that you can ensure by using suitable recording equipment. There is a wide selection of microphones available on the market, so how do you choose the one that’s right for you?
In our previous article we spoke about a number of specific motivations for captioning your audio-visual content. Not only will your content become more accessible for anyone with a hearing disability, but captioning videos has the potential to increase views and engagement, especially from viewers who prefer to watch their videos with the sound turned off. What’s more, with a transcript it becomes much easier for you to translate your content into other languages.