Group items tagged

"Researchers at MIT, Microsoft, and Adobe have developed an algorithm that can reconstruct an audio signal by analyzing minute vibrations of objects depicted in video. In one set of experiments, they were able to recover intelligible speech from the vibrations of a potato-chip bag photographed from 15 feet away through soundproof glass."

"At this point, I should mention what I have neglected to say. Top Secret uses an algorithmic Bluetooth device that tracks your coordinates in the museum, sending you further information and instructions based on your location. This also means that when the voice in your headphone asks you a question, you can respond by moving in certain ways or relocating to specific areas in the galleries. For example, you may be asked to answer a question by walking to the other end of a gallery or waving your notebook (which Top Secret provides you with in the air above your head. "

"Crumpling a thin sheet produces a characteristic sound, comprised of distinct clicking sounds corresponding to buckling events. We propose a physically based algorithm that automatically synthesizes crumpling sounds for a given thin shell animation. The resulting sound is a superposition of individually synthesized clicking sounds corresponding to visually significant and insignificant buckling events. We identify visually signifi- cant buckling events on the dynamically evolving thin surface mesh, and instantiate visually insignificant buckling events via a stochastic model that seeks to mimic the power-law distribution of buckling energies observed in many materials. In either case, the synthesis of a buckling sound employs linear modal analysis of the deformed thin shell. Because different buckling events in general occur at different deformed configurations, the question arises whether the calculation of linear modes can be reused. We amortize the cost of the linear modal analysis by dynamically partitioning the mesh into nearly rigid pieces: the modal analysis of a rigidly moving piece is retained over time, and the modal analysis of the assembly is obtained via Component Mode Synthesis (CMS). We illustrate our approach through a series of examples and a perceptual user study, demonstrating the utility of the sound synthesis method in producing realistic sounds at practical computation times."

"A dedicated algorithm was created to turn one second of browsing on the 4G network into one second of music. The number of connections to the network in different regions of Lithuania controls the volume of the notes being played and their rhythmic distribution, while the amount of data transferred during those sessions determines the notes' pitches."

"Today a growing group of sonic artists engage with plants as collaborators in their processes and creations. The duo Feral Practice invites audience members to sound walks in forests to reflect on ecological and social issues in the vicinity of trees. Sound artist Mileece senses signals from plants to develop sound-generating algorithms that she combines with field recordings to design immersive sound installations, a technology akin to the one used by Tosca Terán to detect activity in mycorrhizal systems which she converts into musical notes. Cristina Ochoa and Eduardo Vindiola read signalling activity in beets and modulate their rhythmic patterns to perform with them. Leslie Garcia studies plant communication to design prosthetic devices that simulate an abstract voice for plants through a process of biofeedback."

"Fermentophone is a multi-sensory installation in which an algorithmically generated musical composition is performed by living cultures of bacteria and yeast. The installation comprises a series of different vessels containing actively fermenting foodstuffs and beverages, which are wired with electronic sensors. Each colorful, odorous, and edible ferment has its own musical vocabulary which is expressed according to microbial activity.( The installation was presented at the Hacking Arts festival at the MIT Media Lab."

"Fermentophone is a multi-sensory installation in which an algorithmically generated musical composition is performed by living cultures of bacteria and yeast."

" DVD-ROM (for MAC and PC) that contains 5 sound compositions generated in ³real time² by a computer algorithm. The works are: Room Piece Twenty-four; Noema; Steiner Suite; Unintending; Scene"

In Resonance: The Journal of Sound and culture "This paper explores the cultural ramifications of music generated by artificial intelligence (AI). Deploying complex algorithms to create original music productions, AI's automation of human authorship may suggest a radically new sonic form. However, its creators have preferred to use its tools to mimic established musical genres from the past. "

"Turning Towards a Radical Listening is an immersive audio-visual metaphor in which an audience is asked to reconcile how their sonic experience is represented, documented, given language and transcribed by AI algorithms over the course of apx. 70 minutes. The resulting nonsense concrete poem demands consideration of how we exist between input and output-holding space for us to tune into what can be lost in translation. "

Locative audio experience at the Brooklyn Museum. "In times of global surveillance scandals, purported no-spy agreements and increasing numbers of whistleblower platforms, with Top Secret International (State 1) Rimini Protokoll enter the global web of state secrets and secret services - the state within the state. In the first part of the tetralogy, which will deal with post-democratic phenomena for two years, an algorithm and a smartphone turn audience members into inconspicuous agents. Playing the role of journalists, visitors will listen in on investigations by foreign intelligence services, put themselves in the shoes of a whistleblower or be fitted with a legend. Between statues in a museum, they can hardly be singled out from other museum visitors. Using subtle gestures, purposeful movements, they access files and archives that open gradually; biographies from politics, journalism and espionage, globally active individuals with security clearance and activists mark out the playing field. The audience members watch and track one another, contact one another, form coalitions or refuse to connect."

Turn 4G network browsing into musical sounds A dedicated algorithm was created to turn one second of browsing on the 4G network into one second of music. The number of connections to the network in different regions of Lithuania controls the volume of the notes being played and their rhythmic distribution, while the amount of data transferred during those sessions determines the notes' pitches."

"Frames and variations, an experiential exhibition, encompassing sound, film and performance, by Hong Kong-based artist Samson Young. The show marks Young's debut solo exhibition with the gallery and will be on view from January 20th to March 4th, 2023, at Petzel's new Chelsea location at 520 W 25th Street. Inspired by the perception of sound and how it is distorted and concealed in cinema, this exhibition is comprised of two new immersive installations that center on the effects of situated listening. Young examines the spatial relationships between the aural source and the viewer's vision, adding to an illusion of sound that encircles the viewer sonically and visually."

"Resemble AI is among a new cohort of generative AI startups aiming to use finely tuned speech models to produce dubs, audiobooks, and other media ordinarily produced by regular human voices. But if such models, perhaps trained on hours of audio provided by actors, were to fall into malicious hands, these companies may find themselves at the center of a PR disaster and perhaps serious liability. So it's very much in their interest to find a way to make their recordings both as realistic as possible and easily verifiable as being generated by AI."

"A UK mathematician has made a public appeal for people to phone a dedicated number so data can be gathered to hone a tool that can diagnose Parkinson's disease by analyzing voice patterns."

"Videogrep is a command line tool written by Sam Lavigne that searches through dialog in video files and makes "supercuts" based on what it finds. It will recognize .srt or .vtt subtitle tracks, and transcriptions that can be generated with vosk. It's like grep, but for video."