Skip Navigation or Skip to Content
My signatureAn animated signature of me signing my first name


Spring 2019
Final mockup

A lyric assistant tool to help aspiring musicians and songwriters craft and revise their song lyrics.


UX Designer


NLP Tool


Louise Larson, Neha Agarwal




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.


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.

Diagram of difficulty vs. value
20 starting points
project selections
We made selections based on tech capabilities, activities, and domains

Defining Basics


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.



Concept Exploration

Sketching on a whiteboard
Whiteboard sketches and ideation

Preliminary Concept Testing

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

  • 9 responses (5 men and 4 women)
  • Ages 18-34
  • All practicing musicians
100% musicians have trouble writing song lyrics
Musicians have trouble writing song lyrics
Most musicians prefer a tool like Grammarly for songwriting
Many musicians are interested in an in-line suggestion tool
Musicians want a tool that helps them brainstorm
Musicians want a tool that helps them brainstorm
Artists would appreciate artist-likeness and phonetic similarity measures
Artist-likeness and phonetic similarity are more desired
Most musicians would pay for this tool
Most musicians would pay some quantity


Quotes from survey
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.



  • is a budding performer and songwriter.
  • struggles with generating the right words to match the music he creates.

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

  • has writer's block.
  • doesn't have time to think of potential combinations of words that rhyme, make sense, and sound good

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 flow diagram
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.


  • 1,000,000 songs/files (273 GB of data)
  • 515,576 dated tracks starting from 1922
  • 44,745 unique artists
  • 2,201,916 asymmetric similarity relationships
  • 43,943 artists with at least one term
  • 7,643 unique terms (Echo Nest tags)
  • 2,321 unique musicbrainz tags


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

However, we gradually gravitated towards focusing primarily on the writing itself, very similar z 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.

barebones wireframe experimentation
Experimental organization
Collapsed view user interface
Collapsed wireframe
Toolbar open user interface
Toolbar wireframe
Analysis user interface
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 features user interface
Premium app wireframe

Risk & Error Recovery

  1. Inappropriate or offensive content recommendations
    • Artists can toggle censorship of expletive words
    • Artists can flag inappropriate content
  2. Unhelpful or uninspiring
    • Nonsensical suggestions in the creative process for songwriting are low-risk
    • Poor suggestions are low-risk unless consistently poor
  3. Suggesting similar content to multiple users
    • Users can take what they want from suggestions
    • Songs will likely still remain quite different; we can flag cover songs

Final Prototype

Collapsed view user interface
Toolbar open user interface
Analysis user interface
Premium features user interface
Premium app


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 email me.