It’s possible that I shall make an ass of myself. But in that case one can always get out of it with a little dialectic. I have, of course, so worded my proposition as to be right either way (K.Marx, Letter to F.Engels on the Indian Mutiny)
Friday, March 15, 2024
GOOD AI
Speaking without vocal cords, thanks to a new AI-assisted wearable device
The adhesive neck patch is the latest advance by UCLA bioengineers in speech technology for people with disabilities
UNIVERSITY OF CALIFORNIA - LOS ANGELES
IMAGE:
PHOTO OF PERSON’S NECK WITH THE DEVICE — A BLACK ADHESIVE SQUARE — ATTACHED OUTSIDE THE THROAT.
People with voice disorders, including those with pathological vocal cord conditions or who are recovering from laryngeal cancer surgeries, can often find it difficult or impossible to speak. That may soon change.
A team of UCLA engineers has invented a soft, thin, stretchy device measuring just over 1 square inch that can be attached to the skin outside the throat to help people with dysfunctional vocal cords regain their voice function. Their advance is detailed this week in the journal Nature Communications.
The new bioelectric system, developed by Jun Chen, an assistant professor of bioengineering at the UCLA Samueli School of Engineering, and his colleagues, is able to detect movement in a person’s larynx muscles and translate those signals into audible speech with the assistance of machine-learning technology — with nearly 95% accuracy.
The breakthrough is the latest in Chen’s efforts to help those with disabilities. His team previously developed a wearable glove capable of translating American Sign Language into English speech in real time to help users of ASL communicate with those who don’t know how to sign.
The tiny new patch-like device is made up of two components. One, a self-powered sensing component, detects and converts signals generated by muscle movements into high-fidelity, analyzable electrical signals; these electrical signals are then translated into speech signals using a machine-learning algorithm. The other, an actuation component, turns those speech signals into the desired voice expression.
The two components each contain two layers: a layer of biocompatible silicone compound polydimethylsiloxane, or PDMS, with elastic properties, and a magnetic induction layer made of copper induction coils. Sandwiched between the two components is a fifth layer containing PDMS mixed with micromagnets, which generates a magnetic field.
Utilizing a soft magnetoelastic sensing mechanism developed by Chen’s team in 2021, the device is capable of detecting changes in the magnetic field when it is altered as a result of mechanical forces — in this case, the movement of laryngeal muscles. The embedded serpentine induction coils in the magnetoelastic layers help generate high-fidelity electrical signals for sensing purposes.
Measuring 1.2 inches on each side, the device weighs about 7 grams and is just 0.06 inch thick. With double-sided biocompatible tape, it can easily adhere to an individual’s throat near the location of the vocal cords and can be reused by reapplying tape as needed.
Voice disorders are prevalent across all ages and demographic groups; research has shown that nearly 30% of people will experience at least one such disorder in their lifetime. Yet with therapeutic approaches, such as surgical interventions and voice therapy, voice recovery can stretch from three months to a year, with some invasive techniques requiring a significant period of mandatory postoperative voice rest.
“Existing solutions such as handheld electro-larynx devices and tracheoesophageal- puncture procedures can be inconvenient, invasive or uncomfortable,” said Chen who leads the Wearable Bioelectronics Research Group at UCLA, and has been named one the world’s most highly cited researchers five years in a row. “This new device presents a wearable, non-invasive option capable of assisting patients in communicating during the period before treatment and during the post-treatment recovery period for voice disorders.”
How machine learning enables the wearable tech
In their experiments, the researchers tested the wearable technology on eight healthy adults. They collected data on laryngeal muscle movement and used a machine-learning algorithm to correlate the resulting signals to certain words. They then selected a corresponding output voice signal through the device’s actuation component.
The research team demonstrated the system’s accuracy by having the participants pronounce five sentences — both aloud and voicelessly — including “Hi, Rachel, how are you doing today?” and “I love you!”
The overall prediction accuracy of the model was 94.68%, with the participants’ voice signal amplified by the actuation component, demonstrating that the sensing mechanism recognized their laryngeal movement signal and matched the corresponding sentence the participants wished to say.
Going forward, the research team plans to continue enlarging the vocabulary of the device through machine learning and to test it in people with speech disorders.
Other authors of the paper are UCLA Samueli graduate students Ziyuan Che, Chrystal Duan, Xiao Wan, Jing Xu and Tianqi Zheng — all members of Chen’s lab.
The research was funded by the National Institutes of Health, the U.S. Office of Naval Research, the American Heart Association, Brain & Behavior Research Foundation, the UCLA Clinical and Translational Science Institute, and the UCLA Samueli School of Engineering.
The wearable technology is designed to be flexible enough to move with and capture the activity of laryngeal muscles beneath the skin.
The two components — and five layers — of the device allow it to turn muscle movement into electrical signals which, with the help of machine learning, are ultimtately converted into speech signals and audible vocal expression.
Researchers have developed a new machine learning system to improve the accuracy and efficiency of sewer-river system models. This innovative approach, detailed in their latest publication, promises to significantly reduce parameter calibration time and enhance model precision in predicting urban water pollution.
The complexity of integrating sewer systems and urban rivers into a comprehensive model has long posed challenges due to extensive computational demands and limited monitoring data. Traditional calibration methods fall short in addressing these challenges effectively.
A recent study (https://doi.org/10.1016/j.ese.2023.100320) published in Environmental Science and Ecotechnology(Volume 18, 2024) introduces an advanced machine learning system designed to improve the accuracy and efficiency of sewer-river system modeling. This innovative technique significantly reduces the time required for parameter calibration and enhances the precision of predictions regarding urban water pollution.
At the heart of this breakthrough research is the ingenious combination of two advanced technologies: Ant Colony Optimization (ACO) and Long Short-Term Memory (LSTM) networks, integrated into a machine learning parallel system (MLPS). ACO is inspired by the foraging behavior of ants to find the most efficient paths, applied here to navigate through the complex parameter space of water models. Meanwhile, LSTM networks, a type of recurrent neural network, excel in recognizing patterns in sequential data, making them ideal for understanding the temporal dynamics of pollutants in sewer-river systems. By marrying these technologies, the researchers have crafted an MLPS capable of performing rapid and precise calibrations of sewer-river models. Traditional methods, often cumbersome and time-consuming, can't match the efficiency or the accuracy of this new approach. Specifically, the MLPS drastically reduces calibration times from potentially months to just a few days, without sacrificing the model's ability to predict pollution levels accurately.
Highlights
A model calibration method is built with model surrogation and algorithm optimization.
The process-based models and machine learning interact in a unique way.
The optimization time of the integrated process-based model could be saved by 89.94%.
The accuracy of complex models can be improved based on limited data.
Dr. Yu Tian, lead author of the study, states, "The integration of Ant Colony Optimization and Long Short-Term Memory algorithms into our machine learning parallel system represents a significant leap forward in environmental management. It allows for rapid, accurate model calibration with limited data, opening new avenues for urban water system planning and pollution control."
MLPS offers a robust solution for the accurate simulation of urban water quality, essential for effective environmental management. Its ability to quickly adapt to new data and scenarios makes it a valuable tool for urban planners and environmental scientists, facilitating the development of targeted pollution control strategies and sustainable water management practices.
This study was supported by the National Key R&D Program of China (2019YFD1100300) and the Fellowship of China Postdoctoral Science Foundation (2020M681105). The authors also acknowledge the State Key Laboratory of Urban Water Resource and Environment, Harbin Institute of Technology (No. 2021TS23).
Environmental Science and Ecotechnology (ISSN 2666-4984) is an international, peer-reviewed, and open-access journal published by Elsevier. The journal publishes significant views and research across the full spectrum of ecology and environmental sciences, such as climate change, sustainability, biodiversity conservation, environment & health, green catalysis/processing for pollution control, and AI-driven environmental engineering. The latest impact factor of ESE is 12.6, according to the Journal Citation ReportTM 2022.
No comments:
Post a Comment