Back to Top

Simile

Simile was a final project for 05-317, The Design of Artificial Intelligence Products, in the Human-Computer Interaction Institute at Carnegie Mellon University. Students were tasked to envision a novel product or service that employs natural language processing (NLP) technology. My team created an NLP lyric analysis tool to help aspiring musicians and songwriters craft and revise their song lyrics.

Simile mockup banner

Roles

UX/UI Design, User Research

Timeline

1 month

Team

Bennett Huffman, Louise Larson, Neha Agarwal

Tools / Methods

Matchmaking, Adobe XD

Vision

Create a lyric analysis tool to help aspiring musicians and songwriters craft and revise their song lyrics.

Discover

Overview

Students were tasked to envision a novel product or service that employs natural language processing (NLP) technology. Using a matchmaking process and a competitive analysis, we narrowed 20 initial ideas down to one value-focused NLP system for a specific set of target users. Ideation process includes finding and/or constructing an appropriate dataset(s) for inferences, accounting for inference errors, and prototyping to our greatest risk.

Starting points on plot
20 starting points
Selecting an idea
We made selections based on tech capabilities, activities, and domains.

Define

Defining Basics

Goal
Assist the songwriting process by analyzing lyrics to help aspiring musicians and songwriters craft and revise their songs.

User Value
Enhances creativity, makes better lyrical choices, more attractive songs, better understanding of own musical choices

Service Value
Better insight into artists across time, genres, platforms, etc.

Difficulty
Moderate

Concept Exploration

Ideation

Whiteboard sketching ideas
White boarding

Survey

We sent a survey to musicians to gauge interest in a tool that helps with song writing.

chart demonstrating songwriting troubles
Musicians have trouble writing song lyrics
Chart showing want for Grammarly-like tool
Many musicians are interested in an in-line suggestion tool
Chart showing musicians want brainstorming tool
Musicians want a tool that helps them brainstorm
Chart showing desired features
Artist-likeness and phonetic similarity are more desired
Chart showing musicians would pay
Most musicians would pay some quantity

Insights

quotes from musicians about songwriting troubles
Quotes about songwriting troubles
What we learned
  1. Originality is a priority
  2. There is sufficient interest in a tool that would suggest (in-line) or generate lyrics based on a set of features
  3. Features of interest: artist likeness, sounds phonetically good, mood/sentiment
What that means

Nearly every musician struggles with writing lyrics. If we can create a tool that doesn’t interfere with the creative process, but provides valuable analytics and recommendations when writers are stuck, they may be willing to pay for this kind of support.

Persona

Mark is a...

Mark wants to finish creating lyrics for a song but......

Design

NLP System

Using the One Million Songs dataset, we could create a comprehensive dataset for our NLP tool with difficult labels already generated. This makes the feasibility of our idea low to moderate.

Our primary difficulty for song analysis then becomes a classification task of labeling user-generated lyrics. Our generation tool can suggest lyrics other artists would use and detect emotion using common sentiment analysis and emotion detection algorithms.

NLP diagram for system
Diagram of NLP system

Pre-labeled data from the One Million Songs dataset includes…

Artist name, song name, lyrics, album, terms, genre, sections, loudness, tempo time signature, key, energy, danceability, segment timbre, duration, similar artists, start/end times for segments, etc.

Figures

Interface Wireframes

We started by exploring what musicians might want to control in an interface.

Experimental songwriting organization
Experimental organization

However, we gradually gravitated towards focusing primarily on the writing itself, very similar to the correctional grammar tool, Grammarly. We wanted to provide artists with a clutter-free writing space with the NLP lyrical tool readily accessible. Our interface is collapsible, with multiple views.

Collapsed view wireframe
Collapsed wireframe
Toolbar open wireframe
Open toolbar wireframe
Analysis view wireframe
Analysis wireframe

Paid users can access additional, generative features which provide in-line suggestions for rhymes and words that suit their lyrical criteria with lyrical suggestions based on genre, emotion, and phonetic rhyming. For example, an artist could look for words similar to those Taylor Swift uses in her songs, words that rhyme, or other words frequently used in pop music in context of his or her song.

Premium view wireframe
Premium wireframe

Risks & Error Recovery

Inappropriate or offensive content recommendations
Unhelpful or uninspiring
Suggesting similar content to multiple users

Deliver

Final Prototype

Collapsed view mockup
Collapsed
Open toobar view mockup
Open toolbar
Analysis view mockup
Analysis
Premium, generative view mockup
Premium

Reflect

We received valuable feedback from musicians, peers, and instructors from surveying musicians and three in-class presentations, pivoting from the patent application process to songwriting. Feedback was positive and helped us refine a viable prototype for our greatest risk and challenge—adoption.

Musicians voiced interest in using a lyrical tool, but have various opinions on payment. Figuring out how to accommodate for the variety of responses and create a viable business model proved difficult. We subsequently addressed this ambiguity by creating a freemium model separating analytical from generative features of NLP.

Feedback from the class expressed concerns over how significantly NLP will improve the creative writing process from a simple rhyming dictionary, and what additional capabilities might be necessary to increase adoption. We used this to define other capabilities that would make such a tool convenient in more just lyric generation, and a roadmap for hooking in our target audience early on in their careers as budding musicians.

For information about other AI-based projects from this class, please contact me at bhuffman@andrew.cmu.edu.