In today’s multicultural society, language is the biggest barrier between the employer and the employee. And now as more opportunities for remote jobs are open, employees’ biggest fear is the language barrier or the different accents that might put them in a tough spot with the company they are applying for. Three Stanford students decided to encounter this problem after one of their own friends lost a customer support job due to his accent.
We decided to help the world understand and be understood,” student Andres Perez Soderi, who is one of the founders of the new firm, told IEEE Spectrum. The friend group-turned-partners include a computer science major from China, an AI-focused management science and engineering major from Russia and a business-oriented MSE major from Venezuela.
After extensive research, the group found out that a lot of work had been done for voice conversion for deep fake technology but very little attention was given to accent translation. “We knew about accent-reduction therapy and being taught to emulate the way someone else speaks in order to connect with them. And we knew from our own experience that forcing a different accent on yourself is uncomfortable,” added Soderi. “We thought if we could allow software to translate the accent [instead], we could let people speak naturally.” Hence, in 2020 they started a company called Sanas which specializes in different accent translation.
Through Sanas, the trio built an algorithm, developed using a neural network that can shift English to and from American, Australian, British, Filipino and Spanish accents. The firm is actively working on adapting accents from other languages as well such as French.
The start-up already has a 14 member staff and customers are lined up for their technology including seven outsourcing companies that provide customer service. Sanas completed a seed funding round of US $5.5 million in late May, bringing their total investment in the product to about $6 million.