Many people want to expand their vocabulary, but casually dropping a new word in conversation when you’re unsure of how it’s pronounced is daunting, and can be a deterrent.

When it comes to spelling and grammar queries, Google has long been a go-to, and now it has turned its attention to pronunciation.

On Friday, Google announced a new “experimental pronunciation feature” that allows you to practise and get feedback on words.

Designed with travellers and language learners in mind, the feature has launched in American English, but will soon expand to include Spanish, Google said.

Language learners can now get audio feedback, and visual clues. Photo: Google

How does it work?

Previously, when you searched for things like ‘how to pronounce quokka’, you could simply play audio and hear the word, Google search product manager Tal Snir explained in a blog post announcing the feature.

“With the new pronunciation feature, you’ll be able to also practise saying ‘quokka’ into your phone’s microphone and receive feedback on what, if anything, can be adjusted in your pronunciation,” he said.

The feature was developed using speech recognition and machine learning – a component of Artificial Intelligence (AI) that describes a machine’s ability to learn and improve over time as it consumes more data.

Speech recognition technology is used to process spoken words by separating them into individual soundbites.

Machine learning is then used to cross reference your pronunciation with the pronunciation it expects.

“For example, if you’re practising how to say ‘asterisk’, the speech recognition technology analyses how you said the word and then, it recognises that the last soundbite was pronounced ‘rict’ instead of ‘uhsk’,” Mr Snir said.

“Based on this, you will receive feedback on how you can improve next time.”

Google will also incorporate images into its English dictionary and translation features to help language learners better understand the meaning of a word.

“Visuals are a helpful way to explain what a word means or even improve the retention rate,” Mr Snir said.

“Starting today, when you look up the translation of a word or its definition, you’ll see images that give you additional context.

“This can be useful with words that have multiple meanings like ‘seal’, or words like ‘avocado’ that aren’t commonly used in all languages or regions.”

Since not all words are easily described with an image, the visual feature will initially be available for nouns, with plans to expand from there.

“We hope these new features give you a creative, more effective way to practise, visualise and remember new words,” Mr Snir said.

“We plan to expand these features to more languages, accents and regions in the future.”