What do I need to use Tywi?

To use the text-only features like across-language chat, you need access to the internet and an updated browser.  For Tywi speech (voice) translation, you need:  (1)  access to the internet (2) an updated browser (3) a decent microphone and (4) speech recognition.  Tywi provides several speech recognition in the cloud, in addition to the speech recognition that is included on PCs, Apple, Android, smartphones and tablets.  The microphone you use also makes a difference.  For example, a microphone built into a PC laptop may create many errors, whereas the Mac laptop built-in microphone creates few errors.  For speech recognition, in addition to the several cloud recognition choices, Tywi on PC laptop, desktop, and the new PC tablets function sensationally with “Dragon Naturally Speaking” downloaded from Nuance.com and installed on your device or on your server (not the freebie app and not the Mac version).  The 3 best browsers for Tywi software are:  Firefox, Chrome, and Windows Edge (September 2017).   Firefox and Chrome both function well with everything including the several cloud recognition software built into Tywi as well as with Dragon.  Microsoft Edge that comes with Windows 10 is good and is also very compatible with Dragon (Nuance.com).  Mac Laptop functions fine with Tywi using Chrome or Firefox.  Tywi currently functions on Safari with all Tywi features except camera-video share.   Safari for Mac Laptop, iPhone and iPad is being updated by Apple in 2017 to meet the new internet regulations that require RTC (Real-Time Communication) technology upon which Tywi is based.  As soon as Apple finishes (estimated October 2017), Tywi will become fully compatible with all Apple devices.  The only browser that is off-limits is the old outdated Internet Explorer that is being deprecated (eliminated) worldwide.

What languages does Tywi support?

To understand how languages function, divide languages between “output” and “input”.

Output:  Tywi outputs 78 languages as text and 35 as synthesized voice (similar to Apple’s Siri).  So, for example, if someone speaks English into Tywi, the audience can choose to read subtitles (text) in 78 languages simultaneously.  The same crowd could choose to hear a translated synthesized voice in 35 languages simultaneously.   Or combo of both.  Output languages include:  Afrikaans, Albanian, Arabic, Armenian, Azeri, Azerbaijani, Basque, Belarusian, Bengali, Bosnian, Bulgarian, Catalan, Chinese Simplified, Chinese Traditional, Croatian, Czech, Danish, Dutch, English, Esperanto, Estonian, Filipino, Finnish, French, Galician, Georgian, German, Greek, Gujarati, Haitian Creole, Hebrew, Hindi, Hmong, Hungarian, Icelandic, Indonesian, Irish, Italian, Japanese, Javanese, Kannada, Khmer, Korean, Lao, Latin, Latvian, Lithuanian, Macedonian, Malay, Maltese, Marathi, Norwegian, Persian, Polish, Portuguese Brazil, Portuguese Europe, Romanian, Russian, Serbian, Slovak, Slovenian, Spanish, Swahili, Swedish, Tamil, Telugu, Thai, Turkish, Ukrainian, Urdu, Vietnamese, Welsh, Yiddish.

Input as text:  Tywi supports 78 languages as typed text input (same languages as above).

Input as voice:  For voice input, Tywi supports any language that is recognized by any speech recognition software that is (1) included in the 42 languages built into Tywi as “cloud speech recognition”, (2) is already installed on your device (like Windows, Apple, Android, Google, smartphones, tablets), or (3) that can be installed by the user (like Nuance.com’s Dragon).  Tywi connects to generic speech engines for the following languages: English (many accents), French (many accents), Spanish (many accents), Arabic (many accents), Afrikaans, Basque, Bulgarian, Catalan, Chinese,  Chinese,  Chinese,  Croatian, Czech, Danish, Dutch, Filipino, Finnish, French,  French,  Galician, German, Greek, Hebrew, Hindi, Hungarian, Icelandic, Indonesian, Italian, Korean, Lithuanian, Malay, Norwegian, Persian, Polish, Portuguese,  Portuguese,  Romanian, Russian, Serbian, Slovak, Slovenian, Spanish,  Swedish, Thai, Turkish, Ukrainian, Vietnamese, Zulu.

How do I choose the correct speech recognition for my voice?

The highest quality speech recognition is Dragon (by Nuance.com) that covers:  English, Spanish, French, German, Italian, Dutch, and Japanese as downloadable software for PC.   Tywi provides several good cloud options including Google, Microsoft, Baidu (Chinese), and Nuance NDEV.   Google is surprisingly good and covers languages and accents that others do not.  However Google has no “training features”, so it does not improve each time you use it, like Nuance does, and may skip sentences while it “catches up” if the speaker talks too fast.  Microsoft Speech is exceptionally fast and quite good if you have a perfectly generic accent and speak very clearly; however, it also does not have a training feature, and most people do not speak clearly when they first begin to use Tywi.  It can take time for clarity of pronunciation to become natural. Nuance NDEV cloud can be used along with the Tywi Voice Profile to recognize each individual speaker’s way of talking, but requires a hefty down-payment in advance.

How do I choose the best automatic translation for my business?

That’s a good question.  The good news is that Tywi offers a wide variety of automatic translation software from which you can choose just by using a pulldown selector.  Importantly, all translation software are not alike.  Each seems to have its advantages and varies wildly by your conversation, the professional words you use, and the amount of slang or expressions you use that may not be “translatable”.   Tywi has set some defaults for certain languages based upon feedback, but the default may not be the best for your subject matter.  The best way to choose a translation software is to run some tests with a native speaker.  Tywi also has a huge staff of highly skilled professional translators in all fields including technical, medical, and financial.  These professional translators can not only help to assess the best translation for your conversation, but can also help by creating a corporate dictionary specifically for your products and vocabulary.  If you test the translation results yourself, take about 3 paragraphs from a previous conversation about your business.  Select text without a lot of foreign names or non-dictionary words (these will need to be added via your dictionary).   Then speak those paragraphs while your linguist tries first one translation option then another.  It is important to remember that you can add new words and translations (or specify that you do not want something translated) in your Tywi personal dictionary depending upon the type of account you have with Tywi.

Accents – what about people who speak with accents?

If your device is not recognizing your words well because you have an accent, try all options listed in the Tywi dropdown.  If the Tywi system is still not recognizing you well, try Dragon by www.Nuance.com that is spectacular at recognizing highly accented voices with amazing accuracy in certain languages.  Includes various native language accents (like New York accent or Southern accent) and also non-native speaker accents, example:  people speaking English with Spanish accent, or Indian, or Russian accent.  Download Dragon from the non-USA website such as www.Nuance.es or www.Nuance.fr  (the Nuance sales agents in the USA often do not realize that Dragon is available in other languages).

How do I move our on-site event online to make it a global webinar?

This is surprisingly easy.  Decide whether you want “audio only” or “camera”.  For audio, just plug a cable from the sound mixer into a separate laptop and use Skype, WebEx, or similar.  Quickly stated, you just need to find a way for that audio or camera feed to go up onto the internet.  It is not complicated, but if you would like us to organize the translation for you (automated or professional), then we need to know what conference software you use and the specifics of what you want to do.  Please send us a Contact Us message with more info.

What creates optimal results?

With the Tywi system, you can achieve perfection, achieve very good results, or achieve medium results.

HUMAN INTERPRETATION:

The “perfection” means human simultaneous interpreters (yours or ours).  The interpreters can interpret using Tywi’s online interpretation software and attendees at a webinar or on-site can hear the interpretation with a simple click on a link.  The result is amazing and is “United Nations style”, in real-time.

AUTOMATIC VOICE TRANSLATION:

The quality of the translation is really driven by the software’s understanding of the original speaker’s words.  The majority of errors occur in understanding the original.  If you say “I have 5 applications” but the software hears “I have 5 apples”, then your audience will say that the “Translation is bad”, but the translation was fine, the original was wrong.   So optimum results are achieved through 3 things:  (1) good speech recognition, (2) speakers who pronounce clearly, and (3)  automatic translation that is pre-prepared for the vocabulary.  One more step can be taken that can make major impact on the accuracy of automatic voice translation:  create a voice profile (about 20 minutes).  This latter is available in conjunction with the Dragon or Nuance selection from the pulldown.

So, what will be the best speech recognition for your purposes and how do you improve automatic translation for your vocabulary?  If you do most of your talking on the telephone, the speech recognition in Android is better than iPhone if you have any kind of accent.  But if you do your speaking on a laptop with headset, Microsoft speech rec is very good if you have a clear, generic broadcast accent and pronounce your worlds well.  Google speech rec is surprisingly good, however it produces more discrepancies while having the advantage of handling more accents.  Then at the top of the speech recognition ladder is Dragon by Nuance.com, the “king” of speech recognition software.  Dragon costs approximately $200 and is available in only about 8 languages, but it understands almost everyone including people with accents, and it is very easy to improve results because it has marvelous training features that not only train to understand your specific voice but words, names and other data can be imported at a click.

TEXT TRANSLATION:

For optimal results in the quality of automatic translation there are 2 ways to improve:  how you speak and your personal dictionaries.  If you speak clearly, in short sentences, try to have a subject and verb, avoid slang and take a very short breath between sentences, your translation will probably be very understandable.  Some languages are almost perfect for certain subjects.  And if you use the personal translation dictionaries Tywi provides and use the speech dictionaries, the accuracy increases.

What if it makes a mistake?

Automation will not be totally perfect, but the interesting phenomena is that the listener’s eyes and ears begin to jump over discrepancies and see and hear what the speaker is trying to communicate.   Some discrepancies may be cute, so just laugh.  Joy is part of the fun of global communication.  The whole world has been using automated translation for years, and everyone wants to communicate, especially in business.  In the global world, people write emails to each other full of typos because they are working outside of their native language, and people use Google Translate on websites to convert the site to their language.  Tywi is about communication – not perfection.  It is LIVE in real-time, and it works.  People understand.  Some languages are more perfect than others.  Absolutely.  Some speakers talk more clearly and are therefore better understood.  If you need perfect, use the feature for human simultaneous interpretation instead of automation.  With Tywi, there is something for everyone.

How good is the automatic translation?

In many languages the automatic translation is amazingly good.  Other languages are less amazing, but all are basically understandable – the viewers/listeners understand what is happening, understand the basic conversation – anywhere from “totally understand everything” to “getting the gist of the conversation”.  But any way you look at it, there is communication.   If you are speaking about general info, business, low tech, and basic medical, then it is quite understandable.  When you begin talking about something that is very industry specific, refine the results by using the dictionary features built into both the speech recognition and into the automated translation selections offered by Tywi.  Try a test first.  If needs more help, prepare the software for your terminology using Tywi’s dictionary feature.  The more advanced speech recognition software like Dragon and Windows and Tywi’s built-in “Cloud Recognition” have ways for you to correct misinterpretations.  And Tywi has ways for you to enter your preferred translations of words and expressions.

Can I use human interpretation not automatic?

Yes, absolutely.  The Tywi interface provides the capability for as many languages as you desire of interpretation.  The interpreters can be located anywhere in the world and can be your interpreters or Tywi interpreters.  Tywi partners with companies that offer sentence-by-sentence interpreters (called “consecutive interpreters”), who arrive in 60 seconds and are paid by the minute.  Our you can use simultaneous interpretation (like the United Nations) organized by your staff or using the Tywi professionals.  The interpreters listen to your conference via telephone, VoIP, or the Web (e.g.. WebEx, Skype, or other), and they interpret into their headsets.  What they say streams to anyone who has chosen to listen on their own devices or the AV team can send through channel earphones.  There will be a little time delay.  For people watching your event online is only about 2 or 3 seconds delay – so very good timing.  If people in the on-site audience are listening (in the same room as the speaker), their delay is about 6 seconds because the sound goes to the web and then comes back again.  But the cost savings are an advantage, and everyone in your audience can listen to a different language or read subtitles, as they choose.

What if we have multiple speakers?

The first solution is a long term solution.  Each speaker can make a “voice profile” sometime in advance.  The profile tells Tywi how the person speaks and pronounces in their language.  Then, the AV team goes to a Tywi webpage that lists all speakers.  When each person speaks, the AV person clicks on the name of that person so that the appropriate voice profile is pulled up by the software.  Once a speaker has a voice profile, every time they speak in future, their voice can generate subtitles or translated voice.   Speakers can also talk in their native language, which makes many people very happy.

Another option that is a bit more complex is to have one person who is the “parrot”.  A “parrot” is someone who repeats every word after all speakers, talking quietly into a headset and our software.  No one hears the parrot, only our software.  This one person trains the speech recognition software for his/her voice.  Then, his/her voice becomes subtitles, and the subtitles turn into computerized voice.

What if the speaker has an accent?

Tywi is really good for people with accents.  First, there are a variety of speech recognition software from which to choose.  also, interestingly, people with accents tend to speak very slowly and clearly, and this can actually be a strong advantage with Tywi, so varies by speaker.  There are also 2 ways to approach the issue of results improvement.  If after trial and error the voice of the accented speaker is still not being well recognized by the selections of Tywi cloud software, we highly recommend using Dragon for PC by Nuance.com (not the freebie version, not Mac version).  The PC version has amazing – amazing! – recognition capabilities for accented speech.  You can to train the software for any voice, and that takes about 20 minutes, but the results are accurate.  Tywi also provides access to Nuance Cloud Recognition using the Tywi voice profile.  If you make a Tywi voice profile (10 minutes), then every time you login, Tywi sends the profile to NDEV for that session.   If the speaker is a guest speaker or prefers not to pre-prepare speech recognition, a “parrot” can be used.  A “parrot” is someone whose voice is well recognized by the Tywi software, and the Parrot repeats the words of the speaker into Tywi.

What feedback should I expect?

When people need language help, we usually receive feedback like ‘Wow!’ or ‘Incredible!’ or at least “I understood what they were trying to say”. Use yourself as an example. Try to imagine someone speaking to you in Chinese or Japanese, and you understand nothing. Then suddenly with Tywi you understand their conversation. Overall, people who need language help are generally grateful. People who do not need language help will spot imperfection more quickly. Someone who speaks both the original language and the translated language may tend to say ‘There is an error in the second subtitle’ or ‘The translation of X really should be Y’. Tywi was created for courtesy and inclusion – to respectfully include people in a conversation who do not speak a language and to include the deaf in everything.  The translations can become more and more perfect by using professional automated translation software – also provided by Tywi – and devoting serious preparation to automation.

What is it like working with speech recognition, is it like the telephone apps?

There are big differences between this approach to speech and the kind of speech software that you encounter when you call a big telephone system.  The bank’s software doesn’t know who you are or how you pronounce your words so it makes mistakes.  When you use Tywi’s Cloud Recognition or if you install Dragon, there is a way to “train” the software to understand you.  That means your results become better and better.

How does the interpreter or parrot hear the original audio?

Any way you can get the audio to the interpreter or parrot and it is loud and clear will be fine.  Telephone and Skype work.  WebEx, GoToMeeting, Adobe Connect – all such conferencing software work well.  The Tywi Presentation Center comes with 2 built-in interpreter channels;  you just download a tiny free software (that will not hurt your computer), following some instructions for one-time setup, and you’re on a roll.  Contact Translate Your World to schedule a consultation on the various options.

What can hurt the results?

There are a few things that can hurt the results.  If you watch out for them and work around, you should be fine:  (1) Not pronouncing your consonants and the ends of words.  When we speak without thinking we tend to slur our words.  If you speak more clearly not only will you make a good impression on your audience, but the software will understand you better.  (2)  Accent and unclear speaking.  If you know that you have an accent or do not speak clearly and you try your speech recognition and it is not working as well as you want, try Dragon.  Dragon is the “king of speech” for a reason.  Often people who are misunderstood on other software will be understood with Dragon (Nuance.com).  (3)  Poor environment.  Some speech rec functions better in a quiet place, others are not as sensitive.  (4) Try a decent microphone – not the most expensive, but not poor quality.  For example, the microphone build into laptop PC is often very poor.  You’ll know quickly when you make some tests with alternatives which works best for you.

What is the Tywi-Hotels?

Tywi-Hotels offers a number of really cool features for across-language speaking and texting.  Tywi enables hotels to speak or text with guests wherever they are – before they arrive, during their stay, if they are lost in the city, and even after they leave.  The hotel can share a personal webpage only with each guest with translated menus from hotel restaurants, local attractions, advertisements from local businesses, etc.  Basically whatever you want it to be.

What is the Tywi for Conferences?

TYWI for conferences is a communication software between the organizers and the exhibitors and attendees plus an advertising mechanism.  The complete conference agenda can be included, plus changes in schedules, biographies, and ways to set up meetings with exhibitors.  It can be used to show subtitles for product demos, breakout sessions, and keynote speeches.  Plus there is an advertising arm for pre-conference advertising, during conference, and post-conference including local eateries and advertising.

What is it like working with Dragon by Nuance.com?

Personally, we like it very much, and highly encourage its use if it handles your native language.  The other option is our cloud recognition that is NDEV, a variation on Dragon in the cloud. Note that the PC version of Dragon is far superior to the Mac version, and the freebie app does not function with Tywi.    Dragon is around $200 and has outstanding recognition, including for accented speakers.  Dragon only requires a few minutes to train and it is easy to improve the recognition if it makes mistakes.  For NDEV, you can make a Tywi voice profile in about 10 minutes, then Tywi calls up your voice profile at the beginning of a meeting and sends it to NDEV.  The way Dragon and NDEV work, they tend to think in full sentences and check the grammar to the best of its ability.  So, it usually creates subtitles and audio that are phrases or sentences.  This “thinking” does mean that it sometimes creates tiny delays while it processes, but depending upon your needs, the results are usually reliable and businesslike.

What about fast speakers?

Fast speakers are an issue no matter whether you use human interpretation or automated.  For automatic voice translation, if the speaker’s voice is going directly to the software, the speaker may test the various types of speech recognition to find which is best personally.  Our guess is that Dragon, by Nuance, will have the best results for this fast speaker if is available in the speaker’s language.  If the fast speaker’s voice is not the voice being recognized, then try using an interpreter or a parrot.   That person will need to condense some of the words – removing unnecessary words.  Fast speakers are always an issue.

Question-answers from a facility

  • How is Tywi used in a webinar?
    Tywi is usually used as a second webpage that contains only the translation and is resized to the lower 1/4 of the screen and superimposed over the presentation webpage (like subtitles at a movie).  Tywi also has an API that enables developers to use the subtitles and computerized voice translations as they prefer.  Because Tywi is a “web page” that means that dozens or hundreds can click to view at the same time, and each person can select their own language.  Our software will remember what language each person requested, and also provide the audio translation if their select it.  Alternatively, you can choose one language and display subtitles on a large monitor or wall.
  • Can we use Tywi on one computer to output to multiple languages simultaneously?
    Tywi is designed for exactly this.  The speaker talks into speech recognition in a variety of ways, and as many people as you desire read subtitles or hear a computerized voice on their computers or mobile devices in their own language. Or you can throw subtitles onto the wall.
  • Are we going to be sending the outputs to your servers? We worry about security.
    Tywi is flotsam on the internet.  Tywi handles around 10 to 20 words at a time.  Tywi actually breaks up (“chunks”) the voice before it leaves your computer, rather than sending streaming audio to a server.  This breaks up any content into unintelligible pieces entering the internet independently with the stream of trillions of bytes of other data.  Files are a greater danger to security – complete blocks of text.  Blocks of text are not available through Tywi.   So, if your company does not choose the “save to database” feature in our software, then Translate Your World is simply a pass-through with no record.  Our software only controls the translation software selection, keeps track of who is using the system, the language selected, and preferences.  If you are using Tywi’s streaming audio conference, the audio is double-encrypted, and the entire Tywi system has major security features (available upon request).
  • Can we have a customized version for our requirements?
    Yes, because we are the developers of Tywi, we can also customize.

Do we provide the interpreter or parrot do you? How does this work?

The interpreter can be yours or ours. A parrot needs to be someone who speaks clearly and who can, for example, repeat the words they hear on a television show into our software.  For highest quality results, either the interpreter or the parrot should be someone who is willing to spend an hour or two learning how to use the software and becoming comfortable.  Our software is professional grade, so not “plug and play” at their level of usage — and the professional approach is what improves the quality of the results. For the interpreter, it will take them about an hour the first time to set up and learn, then in future they will just double-click to join. We offer Parrot and interpreter training webinars.  We can also help the AV team and conference organizers by helping with a test run in advance during which you learn how to maximize the volume of the speaker’s audio signal. That is your sole responsibility — make sure that the voice of the speaker is as loud as possible so that the interpreter hears clearly.  The interpreter or Parrot can be anywhere – in any country. They will listen to the event via the Web. The interpreter or parrot will speak into his/her headset, and the voice can be heard through the interpreter channel by the audiences and can become subtitles in multiple languages or even a translated computerized voice.