Toward the Extraction of Ecologically-Meaningful Soundscape Objects: A New Direction for Soundscape Ecology and Rapid Acoustic Biodiversity Assessment?

Intl Workshop on Big Data Sciences for Bioacoustic Environmental Survey
Efficient methods of biodiversity assessment and monitoring are central to ecological research and crucial in conservation management; technological advances in remote acoustic sensing inspire new approaches. In line with the emerging field of Soundscape Ecology, the acoustic approach is based on the rationale that the ecological processes occurring within a landscape are tightly linked to and reflected in the high-level structure of the patterns of sounds emanating from those landscapes ¿ the soundscape.

Study of Chinese and UK Hit Song Prediction

Proceedings of Computer Music Multidisciplinary Research
The top 40 chart is a popular resource used by listeners to select and purchase music. Previous work on automatic hit song prediction focused on Western pop music. However, pop songs from different parts of the world exhibit significant differences.

The End

"The End" music: Carlos Dominguez, Dartmouth Dance Ensemble dir:John Heginbotham

Upper Valley residents joined the Dartmouth Dance Ensemble with music composed by digital musics graduate student Carlos Dominguez, G'14. Serving as the concert’s finale, “The End” looks at how individuals relate to community and the future. Each performer utilizes nine distinct dance moves in the piece executed in various comnbinations.


Ocelli System: Performance Documentation

The Ocelli system allows a user to perform audiovisual pieces by manipulating cross-modal feedback networks. Two light-sensitive analog oscillators, named Ocelliphones, produce sound which is analyzed, processed, and visualized using Max/MSP/Jitter. The visualizations are subsequently projected back onto the instruments, creating three-dimensional fields of interactive behavioral possibilities that the performer can explore.

YouTube Smash Up

PSY - GANGNAM STYLE (강남스타일) M/V (YouTube SmashUp)

Each week, we take the top 10 videos of YouTube and resynthesize the #1 video using the remaining 9 videos. We’ll continue doing so until one of our videos ends up in the top 10. The process, called “Smash Up” is a new kind of remix/mosaicing process which learns tiny perceptual fragments of audio and video using a computational model of audiovisual perception.

One Million Seconds, Time and Motion Picture Study

One Million Seconds (Time and Motion Picture Study)

One Million Seconds is a study in imploded cinema. Each moment stitches together fragments sampled from 120 full-length motion pictures (24,000,000 frames / 1,000,000 seconds) from the history of cinema. The resulting film is generated from audio-visual fragments, sorted by their audio similarity to a hidden cantus firmus- Glenn Gould's 1981 recording of J. S. Bach's Goldberg Variations. The cantus firmus accompanies the opening titles. Subsequently, the movie consists entirely of matching fragments from the 120 films.

Investigating the Relationship Between Pressure Force and Acoustic Waveform in Footstep Sounds

in Proceedings of the International Conference on Digital Signal Processing (DSP)
In this paper we present an inquiry into of the relationships between audio waveforms and ground reaction force in recorded footstep sounds. In an anechoic room, we recorded several footstep sounds produced while walking on creaking wood and gravel. The recordings were performed by using a pair of sandals embedded with six pressure sensors each. Investigations of the relationships between recorded force and footstep sounds is presented, together with several possible applications of the system.

Creating musical structure from the temporal dynamics of soundscapes

International Conference on Information Science Signal Processing and their Applications (ISSPA)

Heard (excerpt: pages 16 & 17) by magwhyr

Acoustic signal mixtures from the environment often manifest interesting structural properties. These features can be used to generate musical forms, but access is a problem. Here, Probabilistic Latent Component Analysis (PLCA) has been used to automatically extract independent sources from a mixed signal of environmental sounds. Excitation information corresponding to the temporal evolution of independent acoustic sources in the original environment is extracted.

Elementary Sources: Latent Component Analysis for Music Composition

Proceedings of the International Society for Music Information Retrieval
Complexity of music audio signals creates an access prollem to specific musical objects or structures within the source samples. Instead of employing more commonly used audio analysis or production techniques to access features, we describe extraction of sub-mixtures from real-world audio using a Probabilistic Latent Component Analysis-based de- composition tool for music composition.

Distort Them as You Please: The Sonic Artifacts of Compositional Transformation (Ghost in the MP3)

Master's Thesis


"moDernisT" was created by salvaging the sounds lost to mp3 compression from the song "Tom's Diner", famously used as one of the main controls in the listening tests to develop the MP3 encoding algorithm. Here we find the form of the song intact, but the details are just remnants of the original, scrambled artifacts hinting at what once was. This thesis discusses a series of compositions created over the past year that combine the use of external data with intuitive aesthetic decisions.