Articles tagged with Sound Recording
Researchers have developed SmartDJ, an AI-powered editor that allows users to reshape audio experiences with simple words. The system uses language models and diffusion models to interpret high-level requests and generate edited outputs.
Researchers found that environmental and biological factors significantly impact mosquito sound variability between species and individuals. Controlling for these variations is crucial to improve AI-based acoustic classification accuracy.
Researchers at the University of Washington have developed smart headphones that use AI to detect conversation cadence and isolate participants in a noisy soundscape. The prototype was tested with 11 participants, who rated filtered audio more than twice as favorably as baseline sound.
A randomized clinical trial found that self-administered hypnosis significantly reduced hot flash scores and daily interference compared to sham hypnosis. The study suggests that hypnosis delivered through audio files is a clinically significant method for reducing hot flashes in postmenopausal women.
Researchers equipped miniature backpacks with fringe-lipped bats, revealing they hunt large prey like frogs, birds, and small mammals with remarkable success. The study found these small bats conserve energy by spending 89% of their time stationary and striking quickly, succeeding in about 50% of hunts.
Mizzou researchers have discovered a way to 'listen' to molecules moving faster than the speed of sound, using photoacoustic spectroscopy. This technique could help unravel mysteries of astrochemistry and offer clues about the universe's composition, star formation, and life origins.
Research reveals that high temperatures and exposure to heavy metals reduce the frequency and pitch of non-flight wing vibrations in bees. This affects their communication, defense, and buzz-pollination abilities, which are crucial for plant reproduction and biodiversity.
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.
Scientists develop an ambisonic algorithm to simulate precise sound locations in 3D, reproducing sounds with high accuracy and precision. The AudioDome loudspeaker array achieves a spatial resolution comparable to human spatial acuity.
Researchers at the University of Cambridge have developed a handheld device that can accurately record heart sounds without requiring precise placement on the chest. This innovative device, which uses six sensors to capture clearer heart sounds, has the potential to transform heart disease screening and diagnosis.
A new neural network can identify fish activity on coral reefs by sound, faster than human experts, enabling real-time monitoring of fish populations, species identification, and disaster response. This technology has the potential to revolutionize ocean monitoring and research.
Researchers uncover statistically significant structures in humpback whale song, mirroring patterns found in all human languages. This breakthrough highlights a deep commonality between humans and humpback whales, showcasing the role of learning and transmission in complex communication systems.
The project's recordings help improve voice recognition tools by providing diverse speech patterns to train artificial intelligence models. Microsoft has seen significant improvements in recognizing non-standard English speech, with accuracy gains ranging from 18% to 60%, depending on the speaker's disability.
Researchers found that adding audio to a moving subway scene increased balance challenges for people with vestibular problems. The study, published in PLOS ONE, suggests that sounds can be a disruptive factor for those with vestibular hypofunction, a condition resulting in impaired balance.
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 in New Zealand recorded repeating, quack-like sounds in the '80s that were likely a conversation between multiple animals. The sounds, known as Bio-Duck, have never been conclusively identified despite theories that they may be made by Antarctic Minke whales.
Researchers created digital reconstructions of Aztec death whistles and found they produce unique air turbulence, creating a chilling sound. Listeners perceived the whistle's sound as natural and organic, similar to human voices or screams, suggesting a symbolic association with mythological entities.
The exhibition 'ÜberLeben erzählen' at the StadtPalais in Stuttgart sheds light on the 1944 massacre in Sant'Anna di Stazzema, Italy, through personal stories and witness accounts. The show is part of an interdisciplinary project that also explores remembrance, silence, and reflection on the past.
Researchers at Woods Hole Oceanographic Institution found that golfball coral larvae can be encouraged to settle when they hear the sounds of a vibrant, healthy reef. Acoustic enrichment technique showed promise in revitalize degraded sites and help repopulate marine ecosystems.
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.
A pilot study found that voice changes recorded on a smartphone can signal an impending flare-up of COPD symptoms. Researchers analyzed the voices of 28 people with COPD and discovered higher pitched tones and 'jitter' before an exacerbation occurred.
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.
A study by Dr. Pumpki Lei Su and colleagues analyzed over 300 children's home recordings to find that infants form patterns in their sound clusters, producing three categories of sounds. The researchers found significant clustering patterns in typically developing children and those later diagnosed with autism, suggesting a more sponta...
Researchers detected a 24-hour cycle of diving during the spring, with whales swimming deepest in the afternoon to track prey. Two bowhead whales were found to dive in synchrony over a week at a time, even when separated by up to 100 km.
A new study at Tel Aviv University found that geckos experience a sharp increase in metabolic rates when exposed to rocket explosions, leading to energy depletion. The researchers hypothesize that this stress response may apply to many other animals in conflict zones.
Researchers developed a deep learning-based model to estimate rainfall intensity from surveillance audio, achieving a root mean absolute error of 0.88 mm h-1 and a coefficient of correlation of 0.765. This approach offers a new method for high-resolution hydrological sensing, contributing to environmental resilience and urban sensing.
A breakthrough in brain-computer interfaces allows a patient to communicate using only the power of thought. The study, led by Dr. Ariel Tankus, enables individuals with paralysis to signal 'yes' and 'no' through electrical signals in their brain.
Researchers from Max Planck Institute tracked the heart rates of male common noctule bats during flights, revealing a significant increase in heart rate from 6 to 900 beats per minute. The study found that bats consume up to 42% more energy in summer compared to spring, and develop unique strategies to survive in different seasons.
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.
Researchers confirmed that elephant calls contained a name-like component identifying the intended recipient through machine learning analysis. Elephants responded affirmatively to calls addressed to them and less so to those meant for others, suggesting an ability to learn and use arbitrary vocal labels like humans.
Researchers found that infants in English-learning environments were exposed to more spoken language than music, with the gap widening as they get older. The study used daylong audio recordings collected from home environments and crowdsourced annotations through Zooniverse, closing the gap on past studies that relied on parental reports.
Researchers analyzed 130 English-learning infants' vocalizations and found significant cluster patterns of squeals and growls, indicating active play and sound practice. These findings suggest that infant vocal category exploration is a fundamental pathway for language development.
Research in the Alaskan-Aleutian subduction zone found evidence of splay fault uplift generating additional tsunami activity in half of last eight earthquakes. Splay faults can create local tsunamis reaching shores in under 30 minutes, exacerbating coastal destruction.
Researchers used machine learning algorithms to analyze acoustic recordings of marbled murrelets, determining a high accuracy rate exceeding 90% in detecting the species. This method offers a more efficient and labor-intensive way to monitor rare species like the threatened marbled murrelet.
Men with prostate cancer who listened to mindfulness audio recordings during radiation therapy experienced significant reductions in fatigue, sleep problems, anxiety, and depressive symptoms. The study found that the mindfulness intervention was more effective than listening to relaxing music during treatment.
Researchers recorded the first documented case of an amphibian using ultrasound for self-defense against predators. The frog's distress call has a frequency range of 7 kHz to 44 kHz, inaudible to humans. This behavior is likely used to scare away potential predators, such as bats and rodents.
A WVU study found that treating work like a game improves workers' productivity and engagement, but also increases stress levels. Gamification can boost completion times for repetitive tasks, but may push employees past their tolerance threshold, leading to frustration and physical demands.
Researchers simultaneously tagged many humpback whales from the same pod to analyze their vocalization and compare individual calls. This study provides new information about whale behavior and communication, crucial for informing future conservation efforts.
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.
A study by Hokkaido University and Aarhus University reveals a 'nocturnal' surge in vocalization activity among little auks in Arctic summer, contrary to expectations. The findings provide valuable insights into avian behavior under continuous daylight environments.
A recent study conducted at the University of Zurich found that live performances stimulate a stronger emotional response in the brain compared to listening to recorded music. The researchers used magnetic resonance imaging to measure brain activity during both live and recorded music sessions, revealing a significant difference in amy...
Researchers developed a toolkit to translate neuroimaging data into audiovisual representations, enabling scientists to explore brain activity patterns in real time. The tool uses piano sounds for neural activity and violin sounds for blood flow, allowing viewers to discern coupled relationships between the two.
Researchers at University of California - San Francisco have developed a precise map of what is happening in the brain’s auditory cortex when someone hears a melody. The study found that some aspects of music are entwined with how we understand speech, while other important aspects stand alone. The brain uses two sets of neurons to ass...
A recent study published in PLOS Biology found that the human brain can segregate direct speech from its echo, allowing for reliable recognition of echoic speech. This neural separation is essential for understanding conversations in noisy environments and is supported by magnetoencephalography recordings.
A University of Queensland study found humans can correctly identify the emotional context of chickens' clucks, with 69% accuracy. The ability to detect emotional information from vocalisations could improve the welfare of farmed chickens.
Researchers used psychoacoustics to analyze sound frequencies and clarity at the ancient Greek sanctuary of Zeus, revealing that hillside spectators could hear sounds from the hippodrome. The method provides a unique perspective on ancient societies' organization and activity, but its results should be interpreted with caution.
A new study found that an AI-aided home stethoscope can efficiently detect asthma exacerbation in patients of all ages, including children under 5 years old. The device records and analyzes respiratory sounds, providing valuable information for parents and caregivers to identify symptoms early on.
A new deep learning AI tool called ECOGEN has been developed to generate lifelike bird sounds, enhancing the samples of underrepresented species. This allows for improved bird song classification accuracy and contributes to the conservation of endangered bird species.
A team of researchers at Tampere University and Eastern Washington University used weather records to validate the effectiveness of musical characteristics in enhancing data interpretation. The study found that musical sounds can be a powerful complement to traditional data visualization methods.
New research reveals that endangered whales and dolphins inhabit the Hellenic Trench off Greece year-round, challenging seismic surveys and oil and gas exploration. The study confirms the presence of four species, including sperm whales, in both summer and winter, highlighting the need for conservation measures.
A new study by Klick Labs reveals that AI technology can screen for Type 2 diabetes using six to 10 seconds of a person's voice, with high accuracy rates. The research used acoustic features to analyze recordings from over 18,000 participants and identified significant vocal variations between individuals with and without the condition.
A study by Jonathan Middleton demonstrates how digital data can be transformed into sounds, enhancing engagement with complex data points. The custom-built 'data-to-music' algorithm validates a 'fourth dimension' in data interpretation through musical characteristics.
Researchers used AI models to analyze animal sounds in reforested areas, finding that vocalizing species communities mirror biodiversity recovery. The study suggests potential applications for monitoring biodiversity and could lead to certifications or credits for environmental projects.
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.
Researchers found that white English speakers' accents have shifted away from traditional Southern pronunciation since Generation X. The study, published in Language Variation and Change, used archived and new recordings to analyze vowel patterns, finding distinct changes between baby boomers and Gen X.
Researchers found that hard-of-hearing listeners prefer louder levels of lead vocals compared to normal listeners. They also tend to prefer higher frequencies and sparser mixes with fewer frequencies overall.
Scientists successfully reconstructed recognizable versions of Pink Floyd's 'Another Brick in the Wall, Part 1' using nonlinear modeling to decode brain activity. The study identified a unique region in the Superior Temporal Gyrus (STG) responsible for rhythm perception, with electrodes from this region crucial for accurate reconstruct...
WVU linguists analyze speech recordings to determine how intensity and duration shape pronunciation in American English and Spanish. The two-year study aims to redefine sound patterns across languages.
Researchers from FAU Harbor Branch deployed an autonomous wave glider to survey marine managed areas off Puerto Rico, recording grouper mating calls and determining spatiotemporal distribution of the two species. The study highlights the importance of spatial and temporal expansion of existing regulations to protect threatened species.
Researchers have developed a new measurement technique that uses the Kramers-Kronig relation to untangle complex helical light patterns from camera intensity measurements. This allows for single-shot retrieval of orbital angular momentum spectrum information, accelerating and simplifying the process compared to conventional on-axis int...