Microphone and Headset
Your voice - or someone else's voice - reaches the software through some kind of microphone. Example: a headset that plugs into the USB port of your computer. Or a hand-held microphone that plugs into a desktop or laptop computer USB. Or the microphone can be your smartphone, tablet, or other device most of which have built-in microphones. For larger events, the microphone may also be plugged into a mixing board.
Automated translation is software to translate text from one language to another. TYWI has many built-in automatic translation software, and can custom connect to other translation software. Some auto-translation software function better than others for certain languages and subject matters. One of the advantages of TYWI is that the TYWI software provides personal dictionaries so that you have increased control of the results of automated translation.
Speech recognition is built into most devices and also available for download. Speech recognition is software that recognizes what you say and turns your words into text. TYWI translates the text results from speech recognitition, keeps track of your audience and their preferences, then serves to their devices what each member of the audience wants to hear as translated voice or read as subtitles.
Microsoft Windows has built-in speech recognition that is amazingly good if your accent is generic and your pronunciation excellent. And smartphone and tablets have either built-in Google recognition or Apple/Mac speech recognition. The "king" of speech recognition is Dragon Naturally Speaking 13+ by Nuance.com. Dragon is amazing. It can be almost 99% correct, and ignores non-words such as sneezes, coughs, laughter, and unintentional noises.
The type of speech recognition mentioned above is called "dictation style", and is immeasurably more accurate than the telephone system speech recognition that never seems to understand what you say. The reason for the difference is that the telephone systems are guessing what thousands of different voices and accents are trying to say, whereas the "dictation style" speech recognition can be trained in only a few minutes to understand you personally when you speak, your voice, and your pronunciation, even if you have a heavy accent.
“TTS” (text-to-speech) is software that takes text and turns it into a spoken voice, similar to Apple’s Siri. The TYWI translated voices are delivered by the leading online text-to-speech company ReadSpeaker used by websites and mobile apps worldwide in 35+ languages and 100+ voices. (www.ReadSpeaker.com) The non-American-English voices are often lovely and very human. Those languages have a different speaking style, different vowels, and flow well with automation.
For conferences with multiple presenters, sometimes the conference organizer will designate a “parrot”. A parrot is a person who listens and repeats the speaker's words - in the original language - into a headset or microphone. Parrots speak clearly and have trained TYWI software for their voices. The audience does not hear the parrot, only the TYWI software "hears". TYWI will translate what the parrot says. A parrot can be any member of your staff who tried this "repeat what you hear" technique and was comfortable with the resulting subtitles. Parrots are quite useful when there are multiple people giving presentations, because only one or two people (parrots) learn to use the software, but for conferences over 2 hours, two parrots will be needed as they alternate every 30 to 60 minutes.
Using (human) Interpreters
TYWI has a "click to summon an interpreter in 60 seconds" feature for popular languages. This interpreter can be a consecutive language interpreter (sentence-by-sentence) or an ASL interpreter. TYWI also enables simultaneous interpretation on the web - like your own personal United Nations in real-time as you speak. This is extremely useful for business meetings and online events. Use your favorite interpreter, one of your staff, or a pro from Translate Your World. The interpreter may be located almost anywhere in the world. Your audience chooses their output: a) to listen to the interpreter's voice or b) to read subtitles of what the interpreter says created by the interpreter's voice speaking into the software. As an added bonus, the interpreter's voice is automatically translated as subtitles in other languages.
Click language to view User's Manual. May take one minute to load.