Speech Technology in the Midst of the Coronavirus

Article Featured Image

With planes grounded around the globe, lucrative sporting events canceled, corporations losing millions of dollars when their most important tradeshows are called off, and global supply chains suffering massive disturbances, the impact of the novel corona­virus will be heavy on the world’s economy. But speech and other communication technologies could help lessen this impact, helping connect doctors to patients, teachers to students, and businesses to their counterparts around the globe.

Suddenly, companies and international meeting planners that have avoided online events like the plague feel trapped in a new plague, and they are now back-paddling to reverse direction, pouring time and attention into ways to work online that simulate face-to-face team efforts. As entire countries close down, there is a scramble for ways to educate children, hold church services, make friends, and generally have a life, all while distancing ourselves from others. Lack of social interaction is, in fact, very serious psychologically. We need to talk to people for our own mental health. And we desperately need to work to make money. In summary, we need a life even if we are confined to the home.

Zoom Web Conferencing’s market value has exploded as investors shuffle their money from one pile to another with lightening speed. Zoom has accrued as many users in two months as in all of last year, and that number is still going up (Bloomberg Businessweek has dubbed Zoom “the pandemic’s social network”). Webex usage has seen a remarkable rise, as has BlueJeans’ and Google Hangout’s. All as people around the world try to reformat their living and working conditions. 

This is the time for speech technology—and all online communication technologies—to leap into action. We can help the world.


The first leap: distance medical care. As the virus continues to spread, seeking out medical advice risks spreading the virus even further, as those suspecting they have COVID-19 show up at doctor’s offices and ERs. On the flip side, there is the potential for people who require medical interventions to flatly refuse to go to ERs because their fear of exposure to the virus overcomes their need for medical attention.

This circumstance is the opportunity for distance medicine to help improve healthcare by lowering the cost of medical care with a streamlined organization of online visits. The online approach also lowers the doctor’s and nurse’s own physical risk. The new captions (ASR) available on meeting software go a long way toward clarifying the health professional’s words for the elderly, hard of hearing, and the deaf. Importantly, whatever we do now in distance medicine will continue after the COVID-19 threat has faded.

Because the coronavirus is new, much of the initial information about it was incomplete or contradictory, which contributed to confusion and fear spreading across society at large. But this confusion and fear may have been felt more acutely in ethnic language communities, whose members may not have understood the news, yet they saw warnings everywhere and neighbors and children were gossiping.

Ethnic communities need distance healthcare to be available in their language. How can medical staff serve patients whose language is not the same as the doctor’s or the clinic’s, either online or on the phone? Now, distance medicine and other communication applications can quickly integrate APIs of today’s speech translation technology to meet the needs of these communities as well as the needs of almost any country in the world.

APIs translate both sides of the conversation in existing online applications. Or medical staff use a phone call translator comprised of call center software with integrated voice translation technology. While speaking with a patient, both sides of the conversation are automatically translated in real time (a.k.a. “automatic interpretation”). Medical dictionaries and voice modeling are also available to enhance accuracy. The advantage to automatic interpretation is that it functions immediately, costs less than half of an OPI (over the phone interpretation), and cuts any online dual-language visit to about half the time of an OPI. These automatic phone call translators and online APIs also have features to accommodate scripted conversations and pre-translation by professionals to assure 100 percent accuracy.

And when a real human interpreter is the best option, a simple press of an automatic interpretation interface’s touchscreen dials an OPI human interpreter on-demand.

Education: Primary, Secondary, University

With the stay-at-home mandates currently being imposed around much of the world, parents and even governments are pushing students to remain at home. Yet too few schools have provisions for at-home study and instruction. Schools require an online app that can be installed and up and running in no more than one or two days by teachers who may not be experienced in technology. Such apps need to offer a choice of versions according to the bandwidth available at each student’s residence. Such software also should be able to track who attended class and for how long; include composition and testing methodology; have cameras showing the teacher at the front of the classroom for hybrid extended classrooms, or showing the teacher at home for a complete regional shutdown; and include ways to do homework that makes grading easy for the teacher.

Many such online programs have been available and at this point are pretty robust, but the traditional in-class educational structure has long placed a glass ceiling on usage of these technologies. Now the time is right for educational solutions that are compliant with the Children’s Online Privacy Protection Act (COPPA), the Family Educational Rights and Privacy Act (FERPA), and the Americans with Disabilities Act (ADA) to become more widely available.

Title VI requires all primary and secondary schools to provide communication in the native language of student as well as to provide all school information to parents in the parent’s language. Schools have been calling local interpreters (and paying for them) and waiting hours for an interpreter to appear. When Title VI went into effect, there were no grants to go with it, so schools could not comply with the Title VI regulations. But today, with voice translation technology and extended classroom applications, not only can schools continue undeterred, but they can meet Title VI requirements at a fraction of the cost of human interpreters, all while increasing the school’s reach and impact on students.


Corporations, on the other hand, are suddenly asking employees to telework. The meetings that companies usually had in their own conference rooms with their own equipment and IT professionals are suddenly susceptible to an employee’s potentially poor home internet access. As global corporations send their international employees home as well, their usual around-the-world meetings need to continue and, in fact, increase in frequency. Issues of language communication (the inability to understand each other) quickly arise yet can be equally quickly overcome using cross-language online meeting platforms that not only produce subtitles but also use text-to-speech (TTS) to create speech-to-speech for corporate meetings and training in multiple languages at the same time.

The world is working hand in hand to control the coronavirus. This global cooperation is a rare and treasured occurrence. The greatest miracle is the worldwide effort to control the spread by working as partners together to find a vaccine. While a vaccine is being developed, countries around the world are begging for solutions. At press time, places around the world, but especially Europe, Iran, and the United States, are in dire need of solutions, with more hot spots expected to emerge. Anything that the speech technology community can do to help could have a lasting impact on global culture and business. We can do our part by bringing online communication and speech technology directly inside homes here and abroad. 

Sue Reager is president of Translate Your World, a division of Worldwide Tech Connections, developers of software for across-language speech communication. Reach her at sreager@translateyourworld.com or call 877-233-9454, ext. 104.

SpeechTek Covers
for qualified subscribers
Subscribe Now Current Issue Past Issues