Mark Cartwright, Bryan Pardo
SynthAssist is an audio production tool that allows user to interact with synthesizers in a more natural way. Instead of communicating desired sounds to synthesis software using knobs and sliders that control difficult to understand synthesis parameters, users can communicate sound ideas using examples, like existing recordings or vocal imitations. They then listen to and rate the machine's suggestions to give feedback during an interactive search process. This natural approach is more similar to how one might communicate sound ideas to another human. To achieve this, the system treats synthesizer programming as an audio information retrieval task. In addition to programming a synthesizer using this data-driven approach, this approach can also be used to search through large databases of previously existing "factory presets". Watch the demo.
[pdf] Cartwright, M., Pardo, B. VocalSketch: Vocally Imitating Audio Concepts. In Proceedings of the ACM Conference on Human Factors in Computing Systems (CHI), 2015. *Honorable Mention*
[pdf] Cartwright, M., Pardo, B. Audio Production with Intelligent Machines. In Proceedings of the Workshop on Collaborating with Intelligent Machines: Interfaces for Creative Sound at the ACM Conference of Human Factors in Computing Systems (CHI), 2015.
[pdf] Cartwright, M., Pardo, B. SynthAssist: An Audio Synthesizer Programmed With Vocal Imitation. In Proceedings of the ACM International Conference on Multimedia (ACM MM), 2014. *Best Demo Award*
[pdf] Cartwright, M., Pardo, B. Novelty Measures as Cues for Temporal Salience in Audio Similarity. In Proceedings of the ACM Workshop on Music Information Retrieval with User-Centered and Multimodal Strategies (MIRUM), 2012.
[pdf] Cartwright, M., Pardo, B. Interactive Learning for Creativity Support in Music Production. Presented at Semi-Automated Creativity Workshop at Creativity and Cognition, 2011.