(Press-News.org) Overview
Assistant Professor Yuya Hosoda of the Center for IT-Based Education (CITE), Toyohashi University of Technology developed a method for estimating the pitch of vocal cord vibrations of humans from call audio. In this method, the pitch is estimated by integrating the feature quantities extracted from the amplitude and phase spectra of speech on the complex plane. Through experiments, we have demonstrated that the proposed method is not only efficient for call audios whose frequency band is restricted by communication standards, but also works robustly in an environment with background noise.
Details
To prevent the aggravation of neurodegenerative diseases such as Parkinson's disease, the early diagnosis of dysarthria, which is an early symptom, is desirable. Dysarthria is characterized by tremors in voice and disturbed breathing. Although clinical tests diagnose symptoms from the patient's voice, they are time consuming and labor intensive. Additionally, conducting face-to-face interviews in remote locations such as mountainous areas is difficult. Therefore, in this research, we aim to develop a system that automatically diagnoses dysarthria through telemedicine by performing ward rounds via communication devices.
In patients with dysarthria, abnormalities occur during vocalization wherein voice is produced by vocal cord vibrations generated by air released from the lungs in the throat and oral cavity. In this study, our purpose is to estimate the vibration period (pitch) to diagnose the condition of these vocal cord vibrations. Until now, a pitch measurement method that is robust against background noise has been devised based on the feature quantities of the amplitude spectrum obtained via the frequency analysis of speech. However, due to communication standards, call audio via telemedicine lacks some of the desired amplitude spectrum. Thus, extracting feature quantities from an amplitude spectrum with reduced information can lead to errors in pitch estimation.
In this research, we propose a method to extract additional feature quantities from the phase spectrum, a by-product of frequency analysis, in addition to the amplitude spectrum. Deriving a relational equation between the phase shift and pitch in the time and frequency directions, we have verified that pitch can be estimated by applying the observed phase shift to the relational equation. Based on this finding, we extracted new feature quantities from the phase spectrum to quantitatively evaluate the degree of fit to the relational equation. Finally, by integrating the feature quantities extracted from the amplitude spectrum on the complex plane, we compensated for the lack of feature quantities occurring in the pitch estimation of call audio while maintaining robustness against background noise.
The figure shows the pitch estimation results for a call audio. In previous studies that used only the amplitude spectrum, since the amount of information was reduced by band limitation, the pitch was estimated to be higher than the original value. However, in the proposed method, the pitch is accurately estimated from call audio using the feature quantities related to the amplitude and phase spectra. Further, the gross pitch error (GPE), an evaluation index that indicates the percentage of segments where errors occurred, improved to 9.5% in the proposed method, compared to 42.2% in the previous study. In addition, even for call audio with background noise, this method achieved a GPE of 15.2%, demonstrating robustness.
Future Outlook
Although this study focused on pitch estimation to detect abnormalities in vocal cord vibrations, respiratory and oral abnormalities also cause dysarthria. To detect these symptoms, methods that extract feature quantities from the amplitude spectrum have been devised. However, the use of the phase spectrum has not been sufficiently validated. In the future, we will work on extracting relevant feature quantities from the phase spectra for the other cases as well. Further, by comprehensively analyzing these feature quantities, we aim to develop a dysarthria diagnostic system that can function effectively with telemedicine.
This research was supported by Ono Charitable Trust for Acoustics.
Reference
Yuya Hosoda, Arata Kawamura and Youji Iiguni, "Complex-Domain Pitch Estimation Algorithm for Narrowband Speech Signals," IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 31, pp. 2067-2078, 2023, doi: 10.1109/TASLP.2023.3278488.
END
Niigata, Japan – our movements are controlled by multiple neural pathways that connect the brain and spinal cord. In particular, neurons in the cerebral cortex send commands to the motor neurons in the spinal cord and then to the muscles, thus eliciting the required movement. However, this flow of neural information is compromised in amyotrophic lateral sclerosis (ALS)—a widespread progressive neurodegenerative disease in which the muscles gradually atrophy, making movement and breathing difficult. Moreover, a protein called TDP-43 has been found to abnormally ...
A striking image of the invasive orange pore fungus (Favolaschia calocera), which highlights the potential threats the species may pose to Australian ecosystems, has won the third BMC Ecology and Evolution image competition. The competition showcases the wonder of the natural world — both past and present — and celebrates those working to understand it. The winning images are open access and freely available for use under a Creative Commons Attribution 4.0 (CCBY) license.
The overall winning image depicts bright ...
The end of the last Ice Age also marked the end for more than three dozen genera of large mammals in North America, from mammoths and mastodons to bison and saber-toothed cats. Details concerning the precise timing and circumstances, however, have remained murky ever since.
A team of scientists that included Texas A&M University archaeologist Dr. Michael Waters recently focused on the well-known Rancho La Brea Tar Pits in southern California in their quest to provide answers to these questions, resulting in the most exact and detailed timeline for the extinctions that happened during the latter part of the Pleistocene ...
In trials, the antipsychotic drug brexpiprazole (Rexulti) failed to provide a clinically meaningful benefit and increased the risk of death. Yet the US Food and Drug Administration (FDA) has fast tracked its approval, making Rexulti the first antipsychotic for treating agitation in elderly patients with dementia.
At a cost of around $1,400 a month Rexulti’s makers, Otsuka and Lundbeck, are forecasting an additional $1 billion in annual sales, but there are serious questions about the harm-benefit balance of this drug, writes investigative journalist Robert Whitaker in The BMJ today.
The decision may also reverse ...
The University of Arizona College of Nursing was one of 50 institutions nationwide to receive a Health Resources and Services Administration grant to increase the number and diversity of Doctor of Nursing Practice students in clinical rotations at Federally Qualified Health Center partners in southern Arizona.
The project will use the $2.6 million in funding from the HRSA’s Advanced Nursing Education Workforce Program to deploy immersive managed practice adaptable clinical training, or IMPACT, starting in the spring semester of 2024.
The grant will support students pursuing doctorates in the specialty areas ...
Spectacles that are marketed to filter out blue light probably make no difference to eye strain caused by computer use or to sleep quality, according to a review of 17 randomised controlled trials of the best available evidence so far.
Nor did the review find any evidence that blue-light filtering lenses protect against damage to the retina, the light-sensitive tissue at the back of the eye, as included studies did not evaluate this outcome. Blue-light filtering lenses, also known as blue-light blocking spectacles, have been increasingly prescribed or recommended, often by optometrists, ...
In 1956, theoretical physicist David Pines predicted that electrons in a solid can do something strange. While they normally have a mass and an electric charge, Pines asserted that they can combine to form a composite particle that is massless, neutral, and does not interact with light. He called this particle a “demon.” Since then, it has been speculated to play an important role in the behaviors of a wide variety of metals. Unfortunately, the same properties that make it interesting have allowed it to elude detection since its prediction.
Now, a team of researchers led by Peter Abbamonte, a professor of physics at the University of Illinois Urbana-Champaign, ...
Most of us who’ve reached middle age have noticed a slowing in memory and cognition, but scientists don’t have a clear picture of the molecular changes that take place in the brain to cause it.
Now, a study in mice has determined that the most pronounced changes occur in the white matter, a type of nervous system tissue that’s integral to transmitting signals across the brain. The study also examined two treatments — caloric restriction and infusions of plasma from young mice — that affect certain regions of the brain, with ...
In an experiment on how turbulent boundary layers respond to acceleration in the flow around them, aerospace engineers at the University of Illinois Urbana-Champaign observed an unexpected internal boundary layer.
“Not only were we able to identify a new internal boundary layer, but we were able to systematically track its height so we can understand its growth rate. We also noticed that it only formed if our pressure grading, our acceleration, was sufficiently strong. There was a threshold under which we didn't ...
New research to be presented at this year’s Annual Meeting of the European Association for the Study of Diabetes (EASD) in Hamburg, Germany (2-6 October) shows that among people with type 1 and type 2 diabetes, being divorced is associated with a two-thirds higher risk of lower limb amputation (LLA) (amputations below the knee level) compared with being married, and being male is associated with a 57% higher risk of LLA compared with being female. The study is by Dr Stefan Jansson, Örebro University, Örebro, Sweden, and colleagues.
Deterioration in the structure of both large and ...
