What if every phone came equipped with the ability to recognize your voice (and accent) and pronunciation patterns, identifying where you make the most frequent mistakes, and converting it on live calls?
Grit Daily spoke with Claraphone, a tech start-up that does just that. The company, according to its website, is designed to help English-speakers from around the world to understand each other better, customized to every user. The technology automatically improves a person’s pronunciation and clarify of speech during phone calls and/or teleconferencing.
Grit Daily: You had your own adventures before Claraphone. Tell us about those.
Ganna Tymko: I am a born traveler and serial immigrant. I have been to 32 countries so far and worked and lived in five of them before arriving in San Francisco. Every country held some secrets and it was always an adventure to discover them.
GD: For the uninitiated, what is an ‘accent,’ really?
GT: Simply put, an accent is a distinct emphasis of a syllable or word. It is a way of pronouncing a language. Every region has its distinct pronunciations rules. Those rules vary; most languages have at least a few regional variations or dialects. Adults who learn a new language tend to apply pronunciation rules of their mother tongue to the new language. When people hear the word “accent” most think of a foreign accent.
GD: Why “CLARA-fy” it?
GT: Scientific research shows that it is objectively harder for our brains to understand unfamiliar pronunciation. It takes us longer periods of time and higher cognitive inputs to process it. This phenomenon applies to both native and non-native speakers alike. For example, Brits have a hard time understanding New Zealanders.
GD: What does “clarify” mean?
GT: For me, “clarify” means make it easier to understand. For most of us, “clear-sounding speech” equates to “familiar-sounding speech.” My goal here is to help people to understand each other better and facilitate human connection and interaction. The technology I am building will be customizable to both the speaker and the recipient so everyone involved in the conversation will have an easier time understanding. I hope to help people using the technology save time and energy spent on repetitive, follow-up questions and miscommunications.
GD: Why focus on English?
GT: English is the most commonly spoken language around the world. Most recent estimates indicate that there are over 1.5 billion English speakers worldwide — about 20% of the whole world’s population — and that number is growing. My team and I believe that the technology we are building can improve international collaboration by helping people connect better at the individual level.
GD: How do you know you’re not removing slang or colloquialisms in certain cases?
GT: This is a great question! We are training our smart technology to understand a variety of dictionaries including slang and colloquialisms. When in doubt, the technology will leave a particular word or phrase intact.