Articles tagged with Voice
Researchers developed an app to monitor daily voice changes, which can detect early signs of exacerbations in asthma and COPD. By analyzing tone, pitch, pauses, and voice quality, the TACTICAS study found that voice deteriorates as symptoms worsen, allowing for potential treatment.
A recent study by University of Cincinnati researcher Kimberly Hyun found that voices similar to our own are more persuasive, lowering our guard. The closer the vocal quality, the more likely we are to comply with a speaker's words.
Stevie Nicks has made a major gift to establish the Stevie Nicks and Joseph Sugerman, MD, Endowed Chair in Otolaryngology, honoring Dr. Sugerman's impact on patients and the field of ENT. The chair will be held by Michael M. Johns, MD, director of the USC Voice Center.
Researchers found AI voice clones to be up to 20% more intelligible than humans in various testing scenarios, including noise, age, and accent. This breakthrough raises questions about the potential applications of voice cloning technology.
Researchers developed a digital safeguard, My Music My Choice, to protect songs from generative AI cloning. The tool adds imperceptible changes to a song's waveform, making it difficult for AI models to replicate.
Researchers at Aalto University warn that speech technologies can extract valuable personal information, posing risks for insurance premiums, advertising, and harassment. To mitigate this, engineers are developing protective measures, such as separating private info from necessary data transmission and using acoustic technologies to en...
Researchers from UNIGE found that specific areas of the auditory cortex respond to chimpanzee vocalisations, suggesting a shared neural basis for voice recognition. This discovery could have implications for understanding the origin of language development.
A new study found that babies as young as 7 months old can quickly recognize their mothers' voices, but struggle with unfamiliar ones. Maternal speech may also play a role in shaping social processing, influencing how babies respond to new faces.
A team of biomechanical engineers and surgeons has developed a 3D-printing soft robot that can accurately deliver hydrogels to the vocal cord surgical site. The device, which is only 2.7 mm in size, can reconstruct tissues removed during surgery and potentially prevent fibrosis and stiffening of the vocal cords.
A new study reveals that AI voice technology has reached a stage where it can create 'voice clones' that sound just as realistic as human recordings. The study found that both types of AI-generated voices were evaluated as more dominant than human voices and some were also perceived as more trustworthy.
A new study links the size of male proboscis monkeys' noses to their unique vocal characteristics, suggesting a significant impact on individual identity. The findings shed light on the complex interplay between anatomy, acoustics, and social behavior in animals, with potential implications for human communication.
The journal is seeking high-quality submissions that explore the potential of voice and speech analysis in diverse medical applications. Submissions focus on acoustic and voice analysis techniques, voice or vocal phenotyping, and vocal biomarkers in health and medicine.
A new study published in Scientific Reports reveals that audio quality severely affects dogs' ability to recognize and respond to recorded words. Dogs excelled at responding to direct human speech, but struggled with AIC buttons, which lost frequencies necessary for conveying human speech.
Researchers analyzed massive audio recordings to create a dictionary of short melodies in English-language prosody, assigning functions and meanings. They discovered hundreds of basic patterns with linguistic functions, including conveying attitudes such as curiosity or surprise, and identified syntactic rules governing their order.
A study explored how GALs form relationships with youth and the role of training in this process. Findings highlight the critical role of trust and suggest that enhanced training programs, including trauma-informed care and advanced communication skills, can empower GALs to build meaningful connections.
A Northwestern University study discovered a region of the brain processes subtle changes in voice pitch, transforming them into meaningful linguistic information that guides human understanding. The findings challenge long-held assumptions about speech perception and have implications for speech rehabilitation, AI-powered voice assist...
Researchers developed a machine learning tool that screens for comorbid depression and anxiety disorders using acoustic voice signals. The study confirmed that a one-minute verbal fluency test can reliably identify subjects with comorbid AD/MDD, who tend to use simpler words and exhibit reduced variability in phonemic word length.
A recent study published in Frontiers in Communication reveals that people with non-standard accents are more likely to be associated with criminal behaviour, but perceptions vary between accents. The researchers found a significant link between class or status, negative traits, and expected behavior, particularly when it comes to crime.
Researchers at Eötvös Loránd University found that dogs can recognize their owners based on pre-recorded speech, demonstrating an ability to discriminate between familiar voices. Dogs performed well in matching the correct owner with their voice, with performance best when hearing their main owner's voice.
Research by UCL experts found that online training can improve speech intelligibility for both older and younger adults, with a 30% improvement in understanding sentences spoken by new voices. The study suggests that practicing listening to regularly encountered voices could enhance everyday communication.
Researchers are developing a system to instantly conceal and anonymize voices through computer-generated speech. The technology will allow users to control factors like age, gender, and dialect in real-time conversations.
Researchers trained an automatic speech recognizer on recordings from people with dysarthria related to Parkinson's disease, achieving a 30% accuracy improvement. The study, led by Mark Hasegawa-Johnson, provides valuable data for improving voice recognition devices.
A randomized clinical trial found that a voice-activated cognitive behavioral therapy program improved insomnia symptoms in breast cancer survivors. The intervention, delivered in an in-home setting, demonstrated efficacy in reducing sleep disturbances and enhancing overall quality of life.
Researchers at Klick Labs developed an AI technique using vocal biomarkers to predict chronic high blood pressure with up to 84% accuracy. The study used machine learning to analyze hundreds of indiscernible vocal biomarkers, including pitch variability and speech energy distribution patterns.
Researchers developed an AI model using 25 seconds of a person's voice to detect type 2 diabetes, distinguishing between individuals with high accuracy. The model showed strong performance, especially in females aged 60 or older and those with hypertension, aligning with the American Diabetes Association risk score.
A new study published in Scientific Reports confirms a linear relationship between blood glucose levels and voice fundamental frequency, suggesting potential for voice-based glucose monitoring. Researchers at Klick Labs used vocal biomarkers and AI to detect Type 2 diabetes with high accuracy.
Researchers found that adults prioritize cognitive cues over vocal signals when evaluating a child's intelligence or negative emotions, while vocal cues dominate for assessing happiness or helplessness. This study provides insights into the complex dynamics of caregiver-child interactions and their evolutionary roots.
A major clinical trial led by the University of Nottingham found that LSVT LOUD was more effective at reducing the impact of voice problems in people with Parkinson's disease compared to no speech and language therapy or NHS delivered therapy. The treatment improved communication skills, enabling participants to go out and socialize wi...
Researchers found that humans distinguish between voices based on emotional cues, with happy voices being perceived as more human-like. However, the brain's response differs, with AI voices eliciting stronger responses in error detection and attention regulation areas.
A new study by the University of Vienna rejects the idea that opera singers rely on a specialized 'whistle' voice register to produce high-pitched notes. Instead, researchers found that vocal folds vibrate at extremely fast rates to create these sounds, similar to speech and other forms of singing.
Influencers who disable social media comments are perceived as less sincere, less receptive to consumer feedback, and incur professional consequences. This behavior can undermine their ability to connect with followers, even when the displayed comments are mostly negative in nature.
Researchers found that African American English speakers adjust their speech rate and pitch variation when using voice technology, adopting a slower and more monotone register to be better understood. This adaptation helps address disparities in speech recognition systems and aims to improve inclusivity for diverse language varieties.
Researchers at Klick Labs developed an algorithm to detect deepfakes with 80% accuracy by analyzing speech pause patterns, offering a solution to the growing problem of AI-generated content. The study's findings suggest that vocal biomarkers can distinguish between real and fake voices, providing a novel approach to flagging deepfakes.
Researchers developed machine learning models that can recognize emotions in voice recordings as short as 1.5 seconds with high accuracy comparable to humans. The study used three ML models and achieved an accuracy of over 90%, with potential applications in therapy, interpersonal communication technology and more.
A team of UCLA engineers has developed a soft, thin, stretchy device that can detect movement in larynx muscles and translate signals into audible speech with nearly 95% accuracy. The device is made up of two components and uses machine-learning technology to assist patients with voice disorders.
Scientists have discovered that the bat brainstem processes echolocation and communication calls differently, with a stronger response to less frequent calls due to better neural synchronization. The findings may also be relevant to medical applications in humans, such as understanding diseases like ADHD or schizophrenia.
A cross-cultural study found that lower voice pitch makes women and men sound more attractive for long-term relationships and more formidable among other men. Lower male voice pitch also confers formidability and high social status in societies with higher relational mobility, suggesting evolutionary origins.
Dr. Ning Zhang's AntiFake tool uses adversarial techniques to make it difficult for AI tools to read voice recordings, preventing synthesis of deceptive speech. The tool has achieved over 95% protection rate against state-of-the-art speech synthesizers and is accessible to diverse populations.
Researchers found that changes in voice patterns predicted alcohol intoxication with 98% accuracy. The study suggests that smartphones and smart speakers could be used to deliver 'just-in-time interventions' to prevent injuries and deaths from motor vehicle accidents.
Researchers from GIST propose a novel approach to mitigate overfitting in pretrained models used for voice pathology detection, achieving 12.36% and 15.38% improvement in recall using contrastive learning.
A recent study found that animals in the Greater Kruger National Park react with alarm to hearing human voices, fleeing waterholes and abandoning their habitat. The researchers used custom sound systems to compare the fear response of mammals to humans versus lions.
A study found that dogs are more sensitive to speech directed at them than adult-directed speech, with a greater response to female voices. The researchers measured dog brain activity via fMRI and found that the sensitivity was affected by voice pitch and variation.
Researchers developed a new method to estimate vocal cord vibrations pitch from call audio, leading to more accurate dysarthria diagnoses in telemedicine. The method integrates feature quantities extracted from amplitude and phase spectra, demonstrating robustness against background noise.
Neuroscientists at UC Berkeley have successfully reconstructed a recognizable song from brain recordings, capturing the electrical activity of brain regions tuned to music attributes. This breakthrough could enable future brain implants with prosodic content, improving communication for patients with speech disorders.
A new study found that larger group size and polygynous mating systems are linked to deeper male voices in primates. This sex difference is thought to influence mating success through attracting mates or intimidating competitors.
A new study found that combining conventional speech therapy with singing can improve voice problems in individuals with Parkinson's disease. The tele-rehabilitation program showed significant improvements in voice intensity and Voice Handicap Index scores, suggesting a more effective treatment approach.
Lithuanian researchers have developed an AI system to detect early symptoms of Parkinson's disease using voice data. The study found that patients with early-stage Parkinson's often speak in a quieter, more monotonous tone, which can be difficult to notice by ear.
Researchers investigate how voice technology affects consumers' willingness to disclose personal info, with potential benefits for marketers and policymakers. The study reveals that voice technology can both increase and decrease disclosure, depending on the context.
Researchers from Kaunas University of Technology and Lithuanian University of Health Sciences developed an AI-based system to evaluate the 'substitute voice' of laryngectomy patients, allowing for faster detection of pathologies. The Acoustic Substitution Voice Index (ASVI) uses acoustic parameters and artificial intelligence methods t...
A study of 16 cats found they can differentiate their owner's voice from a stranger's, even when tone is changed. This suggests that cats form strong bonds with their owners based on experience of the speaker's voice.
A University of Essex study found that over 90% of deaf people struggled to communicate while wearing masks, with 76% missing vital information and 59% feeling disconnected from society. The researchers hope their findings will inform public policy in future health emergencies.
The use of voice control smart devices in children may impede critical thinking, empathy, and compassion. Devices can't teach children how to behave politely and lack non-verbal communication skills.
Researchers developed a mobile phone app using AI to accurately detect COVID-19 infection in people's voices, outperforming lateral flow tests. The app achieved an accuracy of 89% and can be used for remote testing, enabling rapid screening of populations.
Researchers found that human larynx evolution led to stable voices and controlled pitch without adding new structures. This simplification allowed for the development of complex vocal information, enabling humans to communicate effectively.
Researchers found that hearing one's own voice is critical for sense of agency over speech, helping to understand auditory hallucinations and improve VR experiences. The study's findings suggest a close connection between recognizing one's own voice and feeling in control.
Researchers mapped neural networks in marmoset and macaque monkeys to find that multiple areas in the frontal lobe control vocalization, contradicting a long-held view. This discovery could lead to a better understanding of speech disorders such as stuttering and apraxia.
Researchers found that video radiology reports improved patients' understanding of their results by using lay language and annotated images. The reports were also well-received by patients, with an average rating of 4.7 out of 5.
A study by the University of Cincinnati suggests that transgender and gender diverse people can benefit from better-designed smartphone apps offering voice and communication training software. The app features identified as most critical include feedback, accountability, automated goal setting, and non-interactive elements like videos ...
Researchers developed an AI-based computer algorithm that accurately predicted heart health risks based on voice recordings alone, identifying a high biomarker score associated with increased CAD-related events. The study suggests voice technology could be a powerful screening tool in remote healthcare delivery and telehealth.
A study found that dogs can distinguish their owner's voice from many others, using specific voice properties like pitch and noisiness. In the experiment, dogs successfully identified their owners in 82% of cases, suggesting they use some of the same voice analysis mechanisms as humans.