A SUPER-powered WP Engine Atlas Test Site

Joe&#039;s Atlas Experimentation Site

An initiative at a University of Illinois campus that aims to improve voice recognition software for people with speech difficulties is recruiting adults in the U.S. and Puerto Rico living with <a href="https://alsnewstoday.com/what-is-als/">amyotrophic lateral sclerosis</a> (ALS).
Known as the <a href="https://saa.beckman.illinois.edu/" rel="nofollow">Speech Accessibility Project</a>, it is led by the Urbana-Champaign school&#8217;s Beckman Institute for Advanced Science Technology and takes steps to secure and safeguard participants&#8217; identifying information. Voice recordings from people with other neurological conditions, such as <a href="https://parkinsonsnewstoday.com/news/parkinsons-disease-speech-software-initiative-still-seeking-participants/">Parkinson&#8217;s disease</a>, Down syndrome, stroke or aphasia, and cerebral palsy, are also being collected or sought.
The project ultimately seeks to use the recordings to train voice recognition technologies to better understand people with a broad range of speech patterns and disabilities, including the <a href="https://alsnewstoday.com/speech-problems/">speech difficulties</a> (known as dysarthria) that accompany <a href="https://alsnewstoday.com/living-with-als/">living with ALS</a>.
[recommended-reading id=88913]
<h3>Speech, known to be affected by ALS, can be helped by voice technologies</h3>
Supported by Amazon, Apple, Meta, Google, and Microsoft, the project has shared more than 100,000 speech samples with these companies to date. It plans to make data available to nonprofits and companies that also commit to safeguarding participants&#8217; private information.
&#8220;Just like human listeners, AI [artificial intelligence] listeners do better when they have some experience with the type of speech they&#8217;re listening to,&#8221; Mark Hasegawa-Johnson, the project&#8217;s leader and a University of Illinois Urbana-Champaign professor of electrical and computer engineering, said in a <a href="https://speecaccessibilityproject.beckman.illinois.edu/article">Beckman Institute news article</a>.
Leveraging voice recognition technology can potentially change lives, he said.
&#8220;Stephen Hawking, the physicist, continued his research for decades after he became nonvocal by using an automatic speech synthesizer to communicate on his behalf. Many people with ALS now follow Hawking&#8217;s lead … so that they will be able to communicate with loved ones even when their voices become less intelligible,&#8221; Hasegawa-Johnson added.
Dysarthria can result in difficulty articulating, slow and slurred speech, and a nasal, breathy, or hoarse voice. ALS patients also frequently feel tired after speaking, and can find voice projection challenging.
In the disease&#8217;s later stages, many depend on <a href="https://www.als.org/navigating-als/living-with-als/therapies-care/augmentative-alternative-communication">augmented alternative communication</a> or speech-generating equipment to speak.
<h3>Team Gleason assisting with Speech Accessibility Project</h3>
&#8220;The Speech Accessibility Project seeks to make it possible for people with ALS to communicate using their own voices as long as possible by training automatic speech recognizers to understand voices that have reduced intelligibility because of advancing symptoms of ALS,&#8221; Hasegawa-Johnson said.
<a href="https://teamgleason.org/">Team Gleason</a>, which provides ALS patients with a variety of assistive technology and other support services, shares the project&#8217;s goal of expanding the usefulness of speech recognition tools.
&#8220;Technology has the ability to overcome communication barriers and increase independence,&#8221; said Blair Casey, the group&#8217;s executive director. &#8220;Team Gleason is proud to help accelerate this effort for people living with ALS and anyone else with speech differences. Team Gleason&#8217;s involvement in the Speech Accessibility Project will positively impact millions of people globally whose speech may be challenging for others to understand.&#8221;
People with ALS and caregivers who participate in the project will be compensated for their time with up to $180 in Amazon eCodes. Awards will be given in three increments: $60 after recording 200 samples, another $60 following the 400th recording, and a final $60 installment after recording 600 samples, the university reports.
Due to state privacy laws, people in Illinois, Texas, and Washington currently cannot take part in the project.

University of Illinois recorded voice project recruiting ALS patients

A new advance in technology may pave the way for devices that could allow people with <a href="https://alsnewstoday.com/what-is-als/">amyotrophic lateral sclerosis</a> (ALS) who have lost the ability to speak to communicate using their thoughts alone.
The new tech was described in a study, &#8220;<a href="https://www.nature.com/articles/s41467-023-42555-1">High-resolution neural recordings improve the accuracy of speech decoding</a>,&#8221; which was published in <a href="https://www.nature.com/ncomms">Nature Communications</a>.
ALS is characterized by the <a href="https://alsnewstoday.com/causes-of-als/">progressive dysfunction and death</a> of motor neurons, which are the specialized nerve cells responsible for controlling voluntary movements. This can cause <a href="https://alsnewstoday.com/symptoms-of-als/">symptoms such as muscle weakness</a> throughout the body, including the muscles in the mouth and throat that are needed for speech.
As a consequence, people with ALS, especially those in advanced <a href="https://alsnewstoday.com/stages-of-als/">stages of disease</a>, often have <a href="https://alsnewstoday.com/speech-problems/">difficulty communicating</a> verbally and many lose their ability to speak.
“There are many patients who suffer from debilitating motor disorders, like ALS (amyotrophic lateral sclerosis) or locked-in syndrome, that can impair their ability to speak,&#8221; Gregory Cogan, PhD, co-author of the study at Duke University, said in a <a href="https://neurosurgery.duke.edu/news/brain-implant-may-enable-communication-thoughts-alone">Duke press release</a>.
[recommended-reading id=82931]
<h3>Current available tools &#8216;very slow and cumbersome&#8217;</h3>
Although some tools are available to help people who cannot speak to communicate, they are &#8220;generally very slow and cumbersome,&#8221; Cogan added.
In light of this, researchers have been working on creating better prosthetic devices to allow people with ALS to speak.
One broad strategy for this type of technology is to implant electrical sensors in parts of the brain that are responsible for controlling speech. Theoretically, these sensors could measure and translate brain activity into speech.
The brain is packed with billions of nerve cells, however, and accurately decoding brain signals into speech requires being able to measure and distinguish the activity of individual nerves that are close together. The new study takes a big step toward improving the resolution of this technology.
In previous studies, researchers designed sensors with electrodes that are spaced about three to four millimeters apart.
Here, scientists created a sensor that&#8217;s about twice as dense, with electrodes that are each less than two millimeters apart. The sensor packs 256 electrodes onto a piece of flexible, medical-grade plastic that&#8217;s about the size of a postage stamp.
The sensors were used for preliminary tests in a handful of individuals who were undergoing surgery for conditions such as <a href="https://parkinsonsnewstoday.com/what-is-parkinsons-disease/">Parkinson&#8217;s disease</a>, epilepsy, or a brain tumor.
During the surgery, the sensor was temporarily placed in the brain, and patients were asked to complete a speech repetition task, in which they listened to certain nonword sounds, such as “ava,” “kug,” or “vip,” and then spoke these sounds aloud.
The brain activity data resulting from these tasks was then fed into a machine learning algorithm, so it could learn to decode certain electrical activity as specific sounds.
Results showed the new sensors measured speech-relevant brain activity with more precision and less nonspecific signals, or &#8220;noise,&#8221; compared with older, less-dense sensors.
[recommended-reading id=83944]
<h3>Technology up to 57% accurate in detecting consonant and vowel sounds</h3>
In tests of the sensor&#8217;s ability to recognize phonemes (individual letter sounds), the setup was up to 57% accurate for detecting consonant and vowel sounds.
&#8220;We observed robust decoding for classifying spoken phonemes across all subjects, with maximum accuracy reaching up to 57% &#8230; in predicting both consonants and vowels,&#8221; the researchers wrote.
The new sensor also outperformed older setups at detecting temporal patterns of phoneme use. In other words, it was better able to detect different sounds being made over time, which is conceptually similar to what would be needed for a device that aims to translate brain activity directly into speech.
Although the scientists stressed that more work is needed to continue refining this technology, they concluded this study shows &#8220;micro-scale recordings demonstrated more accurate speech decoding than standard &#8230; electrodes and better resolved the rich spatio-temporal dynamics of the neural underpinnings of speech production.&#8221;

Implant may help patients to speak by decoding their thoughts better

<a href="https://auralanalytics.com/" rel="nofollow">Aural Analytics</a>&#8216; speech analytics software app for <a href="https://alsnewstoday.com/what-is-als/">amyotrophic lateral sclerosis</a> (ALS), intended for use by researchers and doctors working in the disease, has been designated a breakthrough device by the U.S. Food and Drug Administration (FDA).
The designation is meant to speed the development and review of devices with a potential to better treat or diagnose life-threatening or chronic and debilitating conditions.
Called <a href="https://appadvice.com/app/speech-vitals/1501374404" rel="nofollow">Speech Vitals</a>, the ALS mobile application collects short samples of a patient&#8217;s speech, prompted by app-based tasks, to help professionals in monitoring changes, from improvements to disease progression.
[recommended-reading id=83378]
<h3>Changes in patient&#8217;s status as evident in short clips of speech</h3>
<h3></h3>
“Achieving breakthrough designation for Speech Vitals &#8211; ALS is explicit validation that the FDA sees the potential in the Speech Vitals platform to provide for more effective management of this devastating disease,” Jeremy Moore, Aural Analytics&#8217; director of quality assurance and regulatory affairs, said in a <a href="https://www.businesswire.com/news/home/20230329005040/en/FDA-Grants-Breakthrough-Device-Designation-to-Aural-Analytics-for-Speech-Analytics-Software-to-Be-Used-in-Treatment-of-ALS">company press release</a>.
“We look forward to working closely with the agency to continue to develop our platform &#8230; to get it into the hands of the physicians and patients that need it the most,” Moore added.
Due to the progressive weakness in the muscles that control the mouth and vocal cords, people with ALS often experience <a href="https://alsnewstoday.com/speech-problems/">speech problems</a> early in their disease course. These include slow or slurred speech, hoarseness, and difficulty managing tone and pitch.
As speaking abilities tend to worsen over time, changes in speech can be noninvasive, ready markers for monitoring disease progression.
&#8220;We strive to improve patient outcomes by unlocking the valuable brain health data available in the speech signal with scientifically sound and technically viable speech analytics technology,&#8221; the company states on its homepage.
The app is reported to be user-friendly and intended for clinic or home use. But its current use may be limited to clinical trial participants as a way of helping to determine an investigative therapy&#8217;s effectiveness.
Aural Analytics reported, in a <a href="https://auralanalytics.com/aural-analytics-speech-technology-signaled-slowing-of-decline-in-als-patients-speech-and-bulbar-function-in-platform-trial-evaluating-pridopidine-strong/" rel="nofollow">separate release</a>, that the app was used in the Phase 2/3 study (<a href="https://clinicaltrials.gov/ct2/show/NCT04615923">NCT04615923</a>) of oral pridopidine, part of the ongoing <a href="https://clinicaltrials.gov/ct2/show/NCT04297683">HEALEY ALS Platform Trial (NCT04297683)</a> that is testing multiple ALS treatment candidates simultaneously.
While the pridopidine <a href="https://alsnewstoday.com/news/pridopidine-shows-some-potential-in-healey-trial-but-misses-main-goal/">trial failed to meet its primary goal</a> of better physical function, recently diagnosed patients with signs of rapidly progressing ALS showed benefits with treatment.
Significant gains also were observed in two speech measures — speaking rate (how fast someone talks) and articulation rate (how quickly and clearly someone sounds out each word) — across treated patients relative to those given a placebo, as were positive trends in respiratory function.
Technology used in the app currently is available on four continents and works with eight languages, Aural Analytics reported.
Speech Vitals collects a few minutes of speech from a patient engaging in tasks that gauge speech duration, precision of articulation, speaking rate, and other metrics that help to monitor motor conditions that affect speech. The app can be deployed on any device, anywhere in the world.
Aural Analytics also intends to explore its technology as a potential tool to help in <a href="https://alsnewstoday.com/als-diagnosis/">diagnosing ALS</a>. Should Speech Vitals &#8211; ALS be given regulatory approval, the company plans to apply the technology to <a href="https://parkinsonsnewstoday.com/what-is-parkinsons-disease/">Parkinson’s disease</a> and other conditions affecting speech.

Speech Vitals, software app for ALS research and care, gains FDA support

To help those who have lost their ability to speak easily, Georgia Southern University’s <a href="https://chp.georgiasouthern.edu/rehabilitation/ritecare-center-for-communication-disorders/" rel="nofollow">RiteCare Center for Communications Disorders</a> again is recruiting students, faculty, and staff members to make recordings for submission to a <a href="https://vocalid.ai/voicebank/" rel="nofollow">voice bank</a>.
The center’s third annual Voice Drive, which runs through May 2, is aimed at improving communication for people with diseases that rob them of their voice, such as <a href="https://alsnewstoday.com/what-is-als/">amyotrophic lateral sclerosis</a> (ALS), <a href="https://huntingtonsdiseasenews.com/what-is-huntingtons-disease">Huntington’s disease</a>, apraxia, and aphasia.
Participants may make recordings at their home. Once the voices are submitted to <a href="https://vocalid.ai/about-us/" rel="nofollow">VocalID,</a> a voice artificial intelligence company, and stored in its human voice bank, patients with speech loss can use the recordings to help create a voice for themselves.
[recommended-reading id=82022]
<h3>Dysarthria, difficulties with speech, affects most ALS patients</h3>
“A voice is unique to an individual, and the loss of a voice may result in a loss of one’s identity,” Tory Candea, the RiteCare Center’s clinical coordinator, said in a <a href="https://news.georgiasouthern.edu/2023/02/22/ritecare-center-asks-georgia-southern-community-to-lend-their-voice-to-help-others-find-theirs/">university press release</a>. “The use of <a href="https://www.als.org/navigating-als/living-with-als/therapies-care/augmentative-alternative-communication">Augmentative Alternative Communication</a> (ACC) can assist those who have lost their voices, yet the standard voices programmed on ACC devices may sound mechanical, robotic, or unnatural.”
A <a href="https://alsnewstoday.com/symptoms-of-als/">common ALS symptom</a>, estimated to affect more than 80% of patients at some point, is dysarthria, or <a href="https://alsnewstoday.com/speech-problems/">speech problems</a> due to weakness in muscles around the mouth and jaw. Dysarthria can be marked by difficulty pronouncing consonants, slow and slurred speech, trouble moving the tongue, voice quality issues, and weak or overreactive gag reflex.
Patients also frequently <a href="https://www.als.org/navigating-als/resources/fyi-suggestions-and-information-about-speech-changes" rel="nofollow">feel tired after speaking</a>, and weakened lung muscles make voice projection difficult. As ALS advances, people tend to speak less and use shorter sentences as their disorder advances.
It takes about 3,500 sentences to create a complete digital voice, according to RiteCare. Such collection takes an average of five to seven hours, with recordings broken into 10- to 15-minute sessions over several weeks. This year&#8217;s goal is 15,000 sentences, up from the 9,696 collected last year. Participants will need a computer and microphone headset.
“The more individuals who donate their voices, the more options a person who has lost their voice is able to choose from, allowing them the opportunity to find a voice that better matches their personality and identity,” Candea said. “By hosting this voice drive, we hope to help these individuals retrieve control over their voice and improve their overall ability to communicate.”
To register for Voice Drive or to receive more information, send an email to Candea at tcandea@georgiasouthern.edu.
The RiteCare Center assesses and treats those with communication disorders or delays. Services are provided by graduate students in the speech-pathology program at the Georgia Southern University Armstrong Campus. The students are supervised by licensed and certified speech-language pathologists.

Tag: ALS and speech

University of Illinois recorded voice project recruiting ALS patients

Implant may help patients to speak by decoding their thoughts better

Speech Vitals, software app for ALS research and care, gains FDA support

Georgia Southern adding to voice bank for ALS patients, others