According to observations, children with autism frequently speak more slowly than similarly developing kids. They differ in their speech in other ways, most notably in tone, intonation, and rhythm. It is very challenging to consistently and objectively describe these "prosodic" distinctions, and it has been decades since their roots have been identified. Researchers from Northwestern University and Hong Kong collaborated on a study to shed light on the causes and diagnoses of this illness. This method uses machine learning to find speech patterns in autistic children that are similar in Cantonese and English.
There are as many as 1.5 billion English speaking people in the world, including those who speak English as a second language. That may sound like a lot, but that means four out of every five people do not speak English. Therefore, any speech recognition or natural language technology that is built primarily for English speakers will be missing out on 5.9 billion potential customers. That is a big opportunity; but with 6,500 spoken languages still in use throughout the world, it is also a very big challenge. Speech technology has solid roots in American research.
Laura Ng had a dual motive for taking Cantonese classes at Stanford. As a PhD student in anthropology, she was researching the history of Los Angeles' Chinatown. She also wanted to communicate better with her parents, immigrants from China who worked as a seamstress and a cook. In late 2020, she was stunned to hear that Stanford, citing COVID-related budget problems, was laying off its longtime Cantonese teacher, Sik Lee Dennig. As efforts began to save Cantonese at Stanford, the language remained under threat worldwide.
Summary: Machine learning algorithms help researchers identify speech patterns in children on the autism spectrum that are consistent between different languages. A new study led by Northwestern University researchers used machine learning--a branch of artificial intelligence--to identify speech patterns in children with autism that were consistent between English and Cantonese, suggesting that features of speech might be a useful tool for diagnosing the condition. Undertaken with collaborators in Hong Kong, the study yielded insights that could help scientists distinguish between genetic and environmental factors shaping the communication abilities of people with autism, potentially helping them learn more about the origin of the condition and develop new therapies. Children with autism often talk more slowly than typically developing children, and exhibit other differences in pitch, intonation and rhythm. But those differences (called "prosodic differences'" by researchers) have been surprisingly difficult to characterize in a consistent, objective way, and their origins have remained unclear for decades. However, a team of researchers led by Northwestern scientists Molly Losh and Joseph C.Y. Lau, along with Hong Kong-based collaborator Patrick Wong and his team, successfully used supervised machine learning to identify speech differences associated with autism.
Summary: Machine learning algorithms help researchers identify speech patterns in children on the autism spectrum that are consistent between different languages. The data used to train the algorithm were recordings of English- and Cantonese-speaking young people with and without autism telling their own version of the story depicted in a wordless children's picture book called "Frog, Where Are You?" "Using this method, we were able to identify features of speech that can predict the diagnosis of autism," said Lau, a postdoctoral researcher working with Losh in the Roxelyn and Richard Pepper Department of Communication Sciences and Disorders at Northwestern. Finally, the results of the study could inform efforts to identify and understand the role of specific genes and brain processing mechanisms implicated in genetic susceptibility to autism, the authors said. Using a supervised machine-learning analytic approach, we examined acoustic features relevant to rhythmic and intonational aspects of prosody derived from narrative samples elicited in English and Cantonese, two typologically and prosodically distinct languages. Summary: Machine learning algorithms help researchers identify speech patterns in children on the autism spectrum that are consistent between different languages.