We develop new methods in Machine Learning, Signal Processing and Human Computer Interaction to make new tools for understanding and manipulating sound.
penn. Pitch Estimating Neural Networks (PENN)
277ppgs. High-Fidelity Neural Phonetic Posteriorgrams
124CAQE. Crowdsourced Audio Quality Evaluation Toolkit
55MSG. Python
53voogle. This is code for an audio search engine that uses vocal imitations of the desired sound
38audealize-plugin. This is a Juce-based plugin version of Audealize for a DAW
31emphases. Crowdsourced and Automatic Speech Prominence Estimation
27SoundSeek. SoundSeek is a new interface to search through your sound file libraries
22VocalSketchDataSet. vocal imitations of everyday and musical audio concepts
21VocalImitationSet.
18course-deep-learning. Teaching materials for the deep learning course.
18earthquakes. Supporting code for "Automating the Detection of Dynamically Triggered Earthquakes via a Deep Metric Learning Algorithm"
15MCFT. Source code for Multi-resolution Common Fate Transform.
12Siamese-Vocal-Imitations. Classify vocal imitations with a siamese network built in PyTorch. IAL project.
11tria. Python
11WUT. Web Unmixing Toolbox
10mixviz. Jonathan's mixing visualizer
6separation_segmentation_ismir. Separation and segmentation algorithm exploiting the "layering" structure at the beginning of songs
5interactiveaudiolab.github.io. HTML
4audealize_api. An API for Audealize, to encourage fast prototyping of semantic audio applications with Web Audio API.
4pytorch-lightning. The lightweight PyTorch wrapper for high-performance AI research. Scale your models, not the boilerplate.
4DataGlove. A hardware/software project using a Bean and Arduino to build a glove for control of electronic music
3haptuner. A haptic tuner
2nussl-demo. Anonymized companion website for ISMIR 2018 submission
1peakvibe. C++
1