Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 36 of the 37 references it cites were found in a registry or an index.

Novice-AI Music Co-Creation via AI-Steering Tools for Deep Generative Models

Open access
Louie, Ryan, Coenen, Andy, Huang, Cheng Zhi, Terry, Michael, Cai, Carrie J. · 2020 · Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems

Abstract

While generative deep neural networks (DNNs) have demonstrated their capacity for creating novel musical compositions, less attention has been paid to the challenges and potential of co-creating with these musical AIs, especially for novices. In a needfinding study with a widely used, interactive musical AI, we found that the AI can overwhelm users with the amount of musical content it generates, and frustrate them with its non-deterministic output. To better match co-creation needs, we developed AI-steering tools, consisting of Voice Lanes that restrict content generation to particular voices; Example-Based Sliders to control the similarity of generated content to an existing example; Semantic Sliders to nudge music generation in high-level directions (happy/sad, conventional/surprising); and Multiple Alternatives of generated content to audition and choose from. In a summative study (N=21), we discovered the tools not only increased users' trust, control, comprehension, and sense of collaboration with the AI, but also contributed to a greater sense of self-efficacy and ownership of the composition relative to the AI.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1145/3313831.3376739

Cites

36 of 36 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 Key components of Cococo: users can manually write some notes (A), specify which voices and in which time range to request AI-generated music using Voice Lanes (B), click Generate (C) to ask the AI to fill in music given the existing notes on the page, use Semantic Sliders (D) to steer or adjust the AI's output along semantic dimensions of interest (e.g. more surprising, more minor or sad), use the Example-Based Slider (E) to express how similar/different the AI-generated notes should be to an example selection, or audition Multiple Alternatives (F) generated by the AI: users select a sample thumbnail to temporarily substitute it into the music score (shown as glowing notes in this figure (G)), then choose to keep it or go back to their original. Users can also use the Infill Mask's rectangular selection tool (H) to crop a section of notes to be infilled again using AI.
Figure 1 Key components of Cococo: users can manually write some notes (A), specify which voices and in which time range to request AI-generated music using Voice Lanes (B), click Generate (C) to ask the AI to fill in music given the existing notes on the page, use Semantic Sliders (D) to steer or adjust the AI's output along semantic dimensions of interest (e.g. more surprising, more minor or sad), use the Example-Based Slider (E) to express how similar/different the AI-generated notes should be to an example selection, or audition Multiple Alternatives (F) generated by the AI: users select a sample thumbnail to temporarily substitute it into the music score (shown as glowing notes in this figure (G)), then choose to keep it or go back to their original. Users can also use the Infill Mask's rectangular selection tool (H) to crop a section of notes to be infilled again using AI.CC-BY-SA · From the PDF
Figure 2 Use of soft priors to adjust a model's sampling distribution. Darker cells represent higher probabilities. The shape of the distribution is simplified to 1 voice, 7 pitches (rows), and 4 timesteps (columns). In Cococo, the actual shape is 4 voices, 46 pitches, and 32 timesteps.
Figure 2 Use of soft priors to adjust a model's sampling distribution. Darker cells represent higher probabilities. The shape of the distribution is simplified to 1 voice, 7 pitches (rows), and 4 timesteps (columns). In Cococo, the actual shape is 4 voices, 46 pitches, and 32 timesteps.CC-BY-SA · From the PDF
Figure 3 Results from post-study survey comparing the conventional interface and Cococo, with standard error bars.
Figure 3 Results from post-study survey comparing the conventional interface and Cococo, with standard error bars.CC-BY-SA · From the PDF
Figure 4 Common Patterns of using Voice Lanes, visualized using interaction data from 4 archetypal participants (darker-colored segments were performed by users before lighter-colored segments): (A) Voice-byvoice (most common), (B) Temporal Chunks, (C) Combination of Voiceby-Voice and Temporal Chunks, and (D) Ad-hoc Bits
Figure 4 Common Patterns of using Voice Lanes, visualized using interaction data from 4 archetypal participants (darker-colored segments were performed by users before lighter-colored segments): (A) Voice-byvoice (most common), (B) Temporal Chunks, (C) Combination of Voiceby-Voice and Temporal Chunks, and (D) Ad-hoc BitsCC-BY-SA · From the PDF

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

1 more claim about this paper

Create a free account to see every claim other papers make about this one.

See all claims — free account

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 37 references

Research works printed but not linked: 4

  1. Kate Compton and Michael Mateas. 2015. Casual Creators. In Proceedings of the Sixth International Conference on Computational Creativity (ICCC 2015), Hannu Toivonen, Simon Colton, Michael Cook, and Dan Ventura (Eds.). Brigham Young University, Park City, Utah, 228--235. http://computationalcreativity.net/iccc2015/proceedings/10_2Compton.pdf
  2. Monica Dinculescu and Cheng-Zhi Anna Huang. 2019. Coucou: An Expanded Interface for Interactive Composition with Coconet, through Flexible Inpainting. (2019). https://coconet.glitch.me/
  3. Feynman Liang. 2016. BachBot: Automatic Composition in the Style of Bach Chorales. Masters thesis, University of Cambridge (2016).
  4. Ralf Schwarzer and Matthias Jerusalem. 1995. Generalized Self-efficacy Scale. Measures in Health Psychology: A User's Portfolio. Causal and Control Beliefs 1, 1 (1995), 35--37.

Cited by

See all 409

Metadata

Authors
Louie, R., Coenen, A., Huang, C. Z., Terry, M., & Cai, C. J.
Affiliations
  • Northwestern University (US)
  • Google (United States) (US)
  • Independent Researcher, Mountain View, CA, USA
Venue
Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems
Publisher
ACM
Published
2020-04-21
Pages
1-13
OpenAlex
W3031000691
Cited by
271
References
37
Citations by year
2026: 40 · 2025: 75 · 2024: 65 · 2023: 40 · 2022: 34 · 2021: 14 · 2020: 3
FWCI
7.02
Type
conference paper
Language
en
Open access
Locations
CHI Conference on Human Factors in Computing Systems (publishedVersion, cc-by-sa)
Topics
  • Social Sciences › Arts and Humanities › Music › Music Technology and Sound Studies
  • Physical Sciences › Computer Science › Human-Computer Interaction › Innovative Human-Technology Interaction
  • Physical Sciences › Computer Science › Human-Computer Interaction › Usability and User Interface Design
Keywords
novice users, generative music, user trust, self-efficacy, human-AI collaboration, music composition

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Novice-AI Music Co-Creation via AI-Steering Tools for Deep Generative Models. https://app.cochat.ai/papers/10.1145/3313831.3376739
The paper
Louie, R., Coenen, A., Huang, C. Z., Terry, M., & Cai, C. J. (2020). Novice-AI Music Co-Creation via AI-Steering Tools for Deep Generative Models. Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems. https://doi.org/10.1145/3313831.3376739

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.