Finnish Group Developing ASR for Local Languages

Anticipating a rise in foreign-language residents, Finland looks to progress its voice recognition services to be able to recognize a wide range of Finnish accents.

As AI speech recognition technology innovation thrives, Finnish leaders have noticed a lag in local development. To help establish a foundation for voice-activated services in Finnish, broadcaster Yle, Helsinki University, and state development company VAKE launched “Donate Your Speech” — Lahjoita puhetta in Finnish. A publicly funded venture, the project aims to draw speech samples from a large and diverse pool of Finnish speakers, including those learning it as a foreign language.

“Getting non-native Finnish speakers to share their speech is really crucial — especially when you consider how well voice recognition systems understand heavily accented English,” said Pia Erkinheimo of VAKE. “People pause, stumble and mumble a lot more than they think, and it’s important AI learns to recognize that.”

Making progress this year, the “Donate Your Speech” team has already recorded 2,000 hours of speech out of a goal of 10,000 hours. The Language Bank of Finland, an entity within Helsinki University, will manage the accumulated speech. For a nominal fee, the material will be available to anyone, provided they can prove compliance with EU GDPR privacy rules.

“We don’t think of this as large Chinese or US companies benefiting from the project. The point is that we are all in this same ecosystem — including many small Finnish companies — so everyone’s benefiting from it,” Erkinheimo said.

Although the team is optimistic about how the new data will benefit Finnish speakers globally, many common fears about the ethics of AI arose from critics. “There’s a lot of ways in which innocently released data can be misused–a risk that this kind of information can fall into the wrong hands and be manipulated to create deep fakes,” Jyväskylä University lecturer Dave Sayers said, referring to the possibility of impostors fabricating audio samples to yield speech appearing to be authentic.

Aleksi Rossi, one of the leaders of “Donate Your Speech” for Yle, agreed that the potential for abuse exists as new technology emerges in the realms of face and voice recognition. “If someone really wanted to manipulate your voice for criminal purposes they could already do so without your sample,” he explained. “Bringing the threat of misuse into the world actually makes things safer because it prompts the development of new safeguards.”

MultiLingual Staff
MultiLingual creates go-to news and resources for language industry professionals.


Weekly Digest

Subscribe to stay updated

MultiLingual Media LLC