Page 1 of 1 [ 7 posts ] 

ASPartOfMe
Veteran
Veteran

User avatar

Joined: 25 Aug 2013
Age: 66
Gender: Male
Posts: 34,242
Location: Long Island, New York

22 Aug 2022, 12:26 pm

Autistic people demonstrate speech rhythm differences that are consistent across languages, study finds

Quote:
Findings from a machine learning study suggest that some of the speech differences associated with autism are consistent across languages, while others are language-specific. The study, published in the journal PLOS One, was conducted among separate samples of English speakers and Cantonese speakers.

Autism spectrum disorder (ASD) is often accompanied by differences in speech prosody. Speech prosody describes aspects of speech, like rhythm and intonation, that help us express emotions and convey meaning with our words. Atypical speech prosody can interfere with a person’s communication and social abilities, for example, by causing a person to misunderstand others or be misunderstood themselves. The reason these speech differences commonly present among autistic people is not fully understood.

Study author Joseph C. Y. Lau and his team wanted to shed light on this topic by studying prosodic features associated with autism across two typologically distinct languages.

While most related studies have examined English-speaking groups, prosody is used differently across languages. Accordingly, there is reason to believe that the prosodic features associated with autism are also language-specific. With their study, Lau and his colleagues investigated which aspects of speech prosody are reliably associated with autism across languages and which are not.

The participants of the study were native English speakers from the United States and Cantonese speakers from Hong Kong. Among the English group, 55 of the participants were autistic, and 39 were neurotypical. Among the Cantonese group, 28 participants were autistic, and 24 were neurotypical. All participants were asked to narrate the story of a wordless picture book. Their speech was recorded, transcribed, and then divided into individual utterances for further examination.

The researchers used a computer program to extract the speech rhythm and intonation from the narrative samples. Rhythm refers to variations in timing and loudness of speech, while intonation refers to variations in voice pitch. The researchers then used machine learning, a technique that uses computer systems to analyze and interpret data, to try to classify autistic participants versus participants with typical development.

The findings revealed that speech rhythm could reliably classify autistic participants versus neurotypical participants among both the English and Cantonese samples. However, speech intonation could only classify autistic participants versus neurotypical participants in the English sample. Further, when the researchers analyzed a combined dataset of both English and Cantonese speakers, only speech rhythm reliably classified autistic individuals from neurotypical participants.

These results indicate that there were features of speech rhythm that offered enough information for the machine learning algorithm to distinguish between an autistic speaker and a neurotypical speaker. The authors said this falls in line with past research suggesting that autistic people demonstrate reliable differences in stress patterns, speech rate, and loudness of speech. Moreover, the findings suggest that these differences are consistent across two distinct languages.

Notably, intonation only predicted an autism diagnosis among the English sample, but not the Cantonese sample. The study authors say this could be because Cantonese is a tone language, which means that pitch can be used to change the meaning of words


_________________
Professionally Identified and joined WP August 26, 2013
DSM 5: Autism Spectrum Disorder, DSM IV: Aspergers Moderate Severity

“My autism is not a superpower. It also isn’t some kind of god-forsaken, endless fountain of suffering inflicted on my family. It’s just part of who I am as a person”. - Sara Luterman


Elgee
Deinonychus
Deinonychus

Joined: 20 Dec 2021
Gender: Female
Posts: 370
Location: Med West

23 Aug 2022, 11:22 pm

I read this a few days ago; found it very fascinating. Since my diagnosis earlier this year, I've been hanging with some autistic groups. I've met only three or four people who had unusual prosody. All the others sound perfectly normal. I suspect that my prosody may be off just a wee bit; not sure, but I've always hated the sound of my voice on a recorder.



Gammeldans
Deinonychus
Deinonychus

Joined: 13 Dec 2018
Gender: Male
Posts: 300

24 Aug 2022, 2:30 am

Elgee wrote:
I read this a few days ago; found it very fascinating. Since my diagnosis earlier this year, I've been hanging with some autistic groups. I've met only three or four people who had unusual prosody. All the others sound perfectly normal. I suspect that my prosody may be off just a wee bit; not sure, but I've always hated the sound of my voice on a recorder.

What I have noticed is that some people speak with a somewhat monotone voice. It seems more common in people with ASD than NT.
Also, I should add that it often occurs when people think while speaking.

What exactly did you hear? Please explain what you mean by unusual prosody.



Gammeldans
Deinonychus
Deinonychus

Joined: 13 Dec 2018
Gender: Male
Posts: 300

24 Aug 2022, 2:38 am

ASPartOfMe wrote:
Autistic people demonstrate speech rhythm differences that are consistent across languages, study finds
Quote:
Findings from a machine learning study suggest that some of the speech differences associated with autism are consistent across languages, while others are language-specific. The study, published in the journal PLOS One, was conducted among separate samples of English speakers and Cantonese speakers.

Autism spectrum disorder (ASD) is often accompanied by differences in speech prosody. Speech prosody describes aspects of speech, like rhythm and intonation, that help us express emotions and convey meaning with our words. Atypical speech prosody can interfere with a person’s communication and social abilities, for example, by causing a person to misunderstand others or be misunderstood themselves. The reason these speech differences commonly present among autistic people is not fully understood.

Study author Joseph C. Y. Lau and his team wanted to shed light on this topic by studying prosodic features associated with autism across two typologically distinct languages.

While most related studies have examined English-speaking groups, prosody is used differently across languages. Accordingly, there is reason to believe that the prosodic features associated with autism are also language-specific. With their study, Lau and his colleagues investigated which aspects of speech prosody are reliably associated with autism across languages and which are not.

The participants of the study were native English speakers from the United States and Cantonese speakers from Hong Kong. Among the English group, 55 of the participants were autistic, and 39 were neurotypical. Among the Cantonese group, 28 participants were autistic, and 24 were neurotypical. All participants were asked to narrate the story of a wordless picture book. Their speech was recorded, transcribed, and then divided into individual utterances for further examination.

The researchers used a computer program to extract the speech rhythm and intonation from the narrative samples. Rhythm refers to variations in timing and loudness of speech, while intonation refers to variations in voice pitch. The researchers then used machine learning, a technique that uses computer systems to analyze and interpret data, to try to classify autistic participants versus participants with typical development.

The findings revealed that speech rhythm could reliably classify autistic participants versus neurotypical participants among both the English and Cantonese samples. However, speech intonation could only classify autistic participants versus neurotypical participants in the English sample. Further, when the researchers analyzed a combined dataset of both English and Cantonese speakers, only speech rhythm reliably classified autistic individuals from neurotypical participants.

These results indicate that there were features of speech rhythm that offered enough information for the machine learning algorithm to distinguish between an autistic speaker and a neurotypical speaker. The authors said this falls in line with past research suggesting that autistic people demonstrate reliable differences in stress patterns, speech rate, and loudness of speech. Moreover, the findings suggest that these differences are consistent across two distinct languages.

Notably, intonation only predicted an autism diagnosis among the English sample, but not the Cantonese sample. The study authors say this could be because Cantonese is a tone language, which means that pitch can be used to change the meaning of words

Did they find how these people sounded?
I don't trust studies in which they refrain from giving more concrete information.
People say so much about autism: just look at how a person writes on the internet, a person's gait and so on...and you can spot autism.
Well, it sounds simplistic to me although it can be of help sometimes.



Elgee
Deinonychus
Deinonychus

Joined: 20 Dec 2021
Gender: Female
Posts: 370
Location: Med West

24 Aug 2022, 8:58 am

Woman #1) Her voice has a slight lilt to it, almost too gentle sounding, and also sounds like how a voice might sound if talking while trying to maintain a smile. That's my best description.

Woman #2) She was 57 but her pitch/tone sounded almost like a teenager who was slightly nervous.

Man #1) About 20 years old, a slight wavering of pitch as he explained things.

I've heard many others talk, and honestly, they all sounded like any NT in terms of pitch, intonation, inflection, etc, though there might've been another guy who was rather monotone.

As for spotting autism via gait and body mannerisms...I'd think that an autistic person would be better at this than an NT since we have an eye for detail. I can easily spot unusual mannerisms, but this doesn't always mean autism. But since my diagnosis, when I spot unusual mannerisms, I can't help but wonder. I myself don't have unusual mannerisms, as is also the case with the vast majority of other autistics I've met at autistic events. I'm referring to HFA, of course.



Gammeldans
Deinonychus
Deinonychus

Joined: 13 Dec 2018
Gender: Male
Posts: 300

27 Aug 2022, 4:46 am

Elgee wrote:
Woman #1) Her voice has a slight lilt to it, almost too gentle sounding, and also sounds like how a voice might sound if talking while trying to maintain a smile. That's my best description.

Woman #2) She was 57 but her pitch/tone sounded almost like a teenager who was slightly nervous.

Man #1) About 20 years old, a slight wavering of pitch as he explained things.

I've heard many others talk, and honestly, they all sounded like any NT in terms of pitch, intonation, inflection, etc, though there might've been another guy who was rather monotone.

As for spotting autism via gait and body mannerisms...I'd think that an autistic person would be better at this than an NT since we have an eye for detail. I can easily spot unusual mannerisms, but this doesn't always mean autism. But since my diagnosis, when I spot unusual mannerisms, I can't help but wonder. I myself don't have unusual mannerisms, as is also the case with the vast majority of other autistics I've met at autistic events. I'm referring to HFA, of course.

Did woman 1#) have a bright colour in her voice? I think singing or speaking with a smile makes the voice brighter.

An example of the somewhat monotone voice: https://m.youtube.com/watch?v=34m0sXqfDxU



Dear_one
Veteran
Veteran

User avatar

Joined: 2 Feb 2008
Age: 75
Gender: Male
Posts: 5,717
Location: Where the Great Plains meet the Northern Pines

27 Aug 2022, 1:08 pm

I have been noticing how much popular speakers use repetition and pauses to help get their point across. I have always felt at such high risk of being interrupted that my speech is very economical and informative. Unfortunately, to comprehend it, people would need to stop and think, but that is precluded by the next speaker.