If you're an adult with non-standard speech, or know of someone who may be interested in getting involved, you're in the right place! As part of Project Euphonia, we're seeking speech contributions from adults who have difficulty being understood by others. Speech samples can help improve how Google understands individuals with non-standard speech.Record phrases for Google Research
Before you get started
Am I eligible to take part in the Project Euphonia research initiative?
In order to participate in this research initiative, you need to:
- Have access to a mobile device (Android or iOS) or a computer with a microphone.
- Be at least 18 years old.
- Speak and read English fluently.
- Have difficulties being understood by others (not only because of an accent).
What will I do as a participant?
You'll record yourself reading 300 phrases aloud, using a provided online recording tool. These phrases help us study ways we could improve speech recognition technology to better understand non-standard speech.
You are encouraged to take your time recording!
What will I get in exchange for participating?
Participation in our research initiative is voluntary. However, we understand that these recordings take time and energy. As a token of our appreciation, we provide cash-equivalent gift cards to participants who complete phrase sets. Your recordings will be reviewed by a speech and language specialist. If, after review by these specialists, your recordings are deemed suitable for Euphonia research, you will receive a gift card valued at $60 USD (or local currency equivalent) for 300 phrases recorded. Examples of speech that are NOT suitable for Euphonia research include accented speech, and standard speech.
When will I have access to technology that can better understand my voice?
We understand that current speech recognition technology can be frustrating. Project Euphonia is in the early stages of a potentially long research arc. We hope our research leads to product improvements that help your day-to-day life as soon as possible, but realistically this may still be a few years out. The voice samples you share will accelerate our research into helping people with non-standard speech be better understood.