Select Page

Welcome to this brief orientation for working with Spf.io’s AI Captioner.

You have probably seen examples of speech to text errors while using phones, reading live captions, or elsewhere. In some cases, they may cause minor inconveniences; in others, they can change the meaning of a phrase beyond recognition.

For participants who are deaf or hard of hearing, errors in captioning may mean they don’t get the information they need. This is especially true if they miss important names, acronyms, or industry-specific terms they will need later. Furthermore, these errors compound when you begin translating the captions into other languages. Because the best AI translations use whole phrases to capture context, one incorrect word in the original language can affect several in the translation.

Speakers can greatly improve their audience’s experience by cooperating with spf.io’s AI Captioner using several simple techniques.  In this brief instruction, we’ll outline three key concepts to keep in mind: Environment, Articulation, and Familiarity.

Environment

Spf.io’s AI Captioner relies on clear audio, and can’t differentiate between a speaker’s voice and background noise the way humans can. In order to distract the Captioner as little as possible, consider the following:

  • Turn off music and reduce background noise as much as possible. This goes both for speakers and virtual meeting hosts; make sure there’s no extra noise coming through from screen shares, videos, or unmuted participants.

In addition, consider these points for virtual events:

  • Use headphones if available. This reduces the risk of computer audio re-entering the microphone and creating a loop.
  • Use a microphone other than the one built into your computer or device. Even ear-bud microphones are often clearer and reduce echo better than built-in laptop, tablet, and phone mics. For ongoing events, consider investing in a desk microphone or dedicated headset.

Articulation

Spf.io’s AI Captioner is very good at recognizing speech, but has more trouble with mumbling or rapid speech than a human might.

There are many great articles on pacing your speech during presentations, and we recommend looking some up and practicing. Even if your meeting is casual, speaking this way will help the Captioner (and your audience) understand you best. Consider the following basics (and find a handy printable reference sheet here):

  • Speak slowly. This is difficult even for practiced public speakers, but it is the single best thing you can do to help the Captioner understand you.  A simple rule of thumb is, “If it feels like you’re speaking too slowly, it’s probably about right.”
  • Prepare key terms and ideas. Make sure that you know how to pronounce any key terms or names you reference during your content, especially if you plan to incorporate quotes or textual references you did not write yourself. You can also upload this content ahead of time!
  • Practice enunciation and clear speech. When words and syllables blur together, the Captioner has a harder time understanding them. Consider words in your language and area that often get shortened; some common English examples are “gonna” for “going to,” “wanna” for “want to,” and similar phrases. The next set of points can also help with this.

Familiarity

Hands-on practice and familiarity with spf.io’s AI Captioner capabilities doesn’t take long and incredibly beneficial.

  • Provide a list of any relevant names and highly-specialized terms a few days before the event. The Captioner’s vocabulary is extremely large, but it might not know how to correctly spell names, acronyms, or highly-specific industry terms. However, it has a feature called the Auto Replacement Database (ARDB) to compensate for this. It is similar to a customizable Spell Check, and you can use it to train the Captioner on your topic’s unique language.
  • Spend 15-20 minutes speaking into spf.io’s AI Captioner and seeing how accurately it hears you. This will help you identify any speech patterns, phrases, or other nuances that confuse the Captioner. Practice adjusting your speech to see if you can get better results, and take notes on what changes you made to have handy during your event

As you practice, keep in mind that any AI will always have some margin of error. Focus on making sure your key ideas come through, rather than each specific word. If you cannot achieve the quality you hope for with spf.io’s live captioner option, communicate this to your event coordinator. They may be able to coach you further or discuss options like manuscript mode, guaranteeing a great audience experience.

Thank you for learning how to better cooperate with spf.io’s AI Captioner. We trust that it will result in a more satisfying experience for you and your audience.