Breaking News
December 13, 2018 - New study reveals yin-yang personality of dopamine
December 13, 2018 - Long-term Benefit of Steroid Injections for Knee Osteoarthritis Challenged
December 13, 2018 - Adding new channels to the brain remote control
December 13, 2018 - In the Spotlight: A different side of neuroscience
December 13, 2018 - Medical Marvels: Using immunotherapy for melanoma that spread to the brain
December 13, 2018 - Puzzles do not keep dementia away finds study
December 13, 2018 - New mouse model shows potential for rapid identification of promising muscular dystrophy therapies
December 13, 2018 - Study reveals urban and rural differences in prenatal exposure to essential and toxic elements
December 13, 2018 - New collaborative partnership in quest of novel antibiotics
December 13, 2018 - Single tau molecule holds clues to help diagnose neurodegeneration in its earliest stages
December 13, 2018 - AHA Scientific Statement: Low Risk of Side Effects for Statins
December 13, 2018 - What Is Acute Flaccid Myelitis?
December 13, 2018 - How bereaved people control their thoughts without knowing it
December 13, 2018 - Health care democratization underway, according to 2nd annual Stanford Medicine Health Trends Report | News Center
December 13, 2018 - Going Beyond a Single Color
December 13, 2018 - London-based startup launches ‘thedrug.store’ aiming to clean up CBD industry
December 13, 2018 - Loss of tight junction barrier protein results in gastric cancer development
December 13, 2018 - Novel way to efficiently deliver anti-parasitic medicines
December 13, 2018 - RKI publishes new data on disease prevention and utilization of medical services
December 13, 2018 - High-tech, flexible patches sewn into clothes could help to stay warm
December 13, 2018 - Restoring Hair Growth on Scarred Skin? Mouse Study Could Show the Way
December 13, 2018 - Probiotic use may reduce antibiotic prescriptions, researchers say
December 13, 2018 - Drug repositioning strategy identifies potential new treatments for epilepsy
December 13, 2018 - Chronic rhinitis associated with hospital readmissions for asthma and COPD patients
December 13, 2018 - Food poisoning discovery could save lives
December 13, 2018 - Cloned antibodies show potential to treat, diagnose life-threatening fungal infections
December 13, 2018 - Exercise may reduce colorectal cancer risk after weight loss
December 13, 2018 - Russian scientists create hardware-information system for brain disorders treatment
December 13, 2018 - Moderate alcohol consumption linked with lower risk of hospitalization
December 13, 2018 - Nurturing Healthy Neighborhoods | NIH News in Health
December 13, 2018 - Rise in meth and opioid use during pregnancy
December 13, 2018 - Researchers gain new insights into pediatric tumors
December 13, 2018 - FSU study finds racial disparity among adolescents receiving flu vaccine
December 13, 2018 - Study investigates attitudes toward implementation of ‘sex as a biological variable’ policy
December 13, 2018 - Drug cocktail induces cancer cell death by switching off energy supply
December 13, 2018 - Baculovirus virion completely eliminates liver-stage parasites in mouse model
December 13, 2018 - Researchers create noninvasive technology that detects when nerve cells fire
December 13, 2018 - Allen Institute for Immunology to partner with CU Anschutz to understand dynamics of human immune system
December 13, 2018 - Inability to do daily living tasks delays discharge of mental health patients
December 13, 2018 - Treating patients with hypertension induced albuminuria
December 13, 2018 - New substance could improve efficacy of established breast cancer treatments
December 13, 2018 - Scientists develop new stem cell line to study conversion of stem cells into muscle
December 13, 2018 - Re-programming the body’s energy pathway boosts kidney self-repair
December 13, 2018 - Research findings could help improve treatment of anxiety and post-traumatic stress disorders
December 13, 2018 - The Microbiome Movement announce Microbiotica as official industry partner
December 13, 2018 - New study reveals potential benefits of cEEG monitoring for infant ICU patients
December 13, 2018 - Whole-body imaging PET/MRI offers information to guide treatment options for prostate cancer
December 13, 2018 - International investigators fight against the negative campaign on benzodiazepines
December 13, 2018 - Targeting biochemical pathway may lead to new therapies for alleviating symptoms of anxiety disorders
December 13, 2018 - FDA Approves Tolsura (SUBA®-itraconazole capsules) for the Treatment of Certain Fungal Infections
December 13, 2018 - Are scientists studying the wrong kind of mice?
December 13, 2018 - Computer memory: A scientific team builds a virtual model of a key brain region
December 13, 2018 - Visual inspection alone is insufficient to diagnose skin cancer
December 13, 2018 - Paternal grandfather’s access to food associated with grandson’s mortality risk
December 13, 2018 - Our brain senses angry voices in a flash, study shows
December 13, 2018 - PM2.5 Exposure Linked to Asthma Rescue Medication Use
December 13, 2018 - Can’t exercise? A hot bath may help improve inflammation, metabolism, study suggests
December 13, 2018 - Can artificial intelligence help doctors with the human side of medicine?
December 13, 2018 - Virginia Tech and UC San Diego researchers team up to develop nonopioid drug for chronic pain
December 13, 2018 - NIH offers support for HIV care and prevention research in the southern United States
December 12, 2018 - Activating brain region could revive the urge to socialize among opioid addicts
December 12, 2018 - Relationship impairment appears to interfere with seeking mental health treatment in men
December 12, 2018 - Sleep, Don’t Cram, Before Finals for Better Grades
December 12, 2018 - Effective treatments for urticarial vasculitis
December 12, 2018 - Gun violence is a public health issue: One physician’s story
December 12, 2018 - The Science of Healthy Aging
December 12, 2018 - Yes to yoghurt and cheese: New improved Mediterranean diet
December 12, 2018 - Researchers uncover a number of previously unknown insecticide resistance mechanisms
December 12, 2018 - Regulating the immune system’s ‘regulator’
December 12, 2018 - In breaking bad news, the comfort of silence
December 12, 2018 - Study finds upward link between alcohol consumption and physical activity in college students
December 12, 2018 - FDA issues warning letter to Zhejiang Huahai Pharmaceutical involved in valsartan recall
December 12, 2018 - Weight history at ages 20 and 40 could help predict patients’ future risk of heart failure
December 12, 2018 - Presence of antiphospholipid antibodies tied to first-time MI
December 12, 2018 - DNA analysis finds that stethoscopes are teaming with bacteria
December 12, 2018 - New study could help inform research on preventing falls
December 12, 2018 - Women and men with heart attack symptoms receive different care from EMS
December 12, 2018 - Disrupted biological clock can contribute to onset of diseases, USC study shows
December 12, 2018 - New publications generate controversy over the value of reducing salt consumption in populations
December 12, 2018 - New data from TAILORx trial confirms lack of chemo benefit regardless of race or ethnicity
New technology can help people with hearing loss better understand speech

New technology can help people with hearing loss better understand speech

image_pdfDownload PDFimage_print

Future hearing aid users will be able to target their listening more accurately thanks to new Danish technology. A researcher from Aalborg University uses machine learning to teach a computer program how to remove unwanted noise and enhance speech.

One of the main challenges for people with hearing loss is understanding speech in noisy surroundings. The problem is referred to as the cocktail party effect because situations where many people are talking at the same time often make it very hard to distinguish what is being said by the individual you are talking to.

Even though most modern hearing aids incorporate various forms of speech enhancement technology, engineers are still struggling to develop a system that makes a significant improvement.

PhD student Mathew Kavalekalam from the Audio Lab Analysis at Aalborg University is using machine learning to develop an algorithm that enables a computer to distinguish between spoken words and background noise. The project is done in conjunction with hearing aid researchers from GN Advanced Science and is supported by Innovation Fund Denmark.

Computer listens and learns

“The hearing center inside our brains usually performs a string of wildly complicated calculations that enables us to focus on a single voice – even if there are many other people talking in the background,” explains Mathew Kavalekalam, Aalborg University. “But that ability is very difficult to recreate in a machine.”

Mathew Kavalekalam started out with a digital model that describes how speech is produced in a human body, from the lungs via throat and larynx, mouth and nasal cavities, teeth, lips, etc.

He used the model to describe the type of signal that a computer should ‘listen’ for when trying to identify a talking voice. He then told the computer to start listening and learning.

Noise isn’t just noise

“Background noise differs depending on the environment, from street or traffic noise if you are outside to the noise of people talking in a pub or a cafeteria,” Mathew Kavalekalam says. “That is one of the many reasons why it is so tricky to build a model for speech enhancement that filters the speech you want to hear from the babbling you are not interested in.”

At Aalborg University Mathew Kavalekalam played back various recordings of voices talking to the computer and gradually added different types of background noise at an increasing level.

By applying this machine learning, the computer software developed a way of recognizing the sound patterns and calculating how to enhance the particular sound of talking voices and not the background noise.

Fifteen percent improvement

The result of Kavalekalam’s work is a piece of software that can effectively help people with hearing loss better understand speech. It is able to identify and enhance spoken words even in very noisy surroundings.

So far the model has been tested on ten people who have been comparing speech and background noise with and without the use of Kavalekalam’s algorithm.

The test subjects were asked to perform simple tasks involving color, numbers and letters that were described to them in noisy environments.

The results indicate that Kavalekalam may well have developed a promising solution. Test subjects’ speech perception improved by fifteen percent in very noisy surroundings.

Snappy signal processing

However, there is still some work to be done before Mathew Kavalekalam’s software finds its way into new hearing aids. The technology needs to be tweaked and tuned before it is practically applicable.

The algorithm needs to be optimized to take up less processing power. Even though technology keeps getting faster and more powerful, there are hardware limitations in small, modern hearing aids.

“When it comes to speech enhancement, signal processing needs to be really snappy. If the sound is delayed in the hearing aid, it gets out of sync with the mouth movements and that will end up making you even more confused,” explains Mathew Kavalekalam.

Fact Box

– One in six Europeans experiences various degrees of hearing impairment. Almost everyone loses part of their hearing as they age.

– Hearing loss often manifests itself in problems when trying to participate in conversations with more than one person talking. This can lead to isolation as people with hearing loss often choose to withdraw from social gatherings where they have to spend a lot of energy trying to keep up with what is being said.

Tagged with:

About author

Related Articles