Project by: 

Eloisa Cusi

High Concept Statement: 

Headspace for vocal improvement

Platform:

iPhone

Category:

Lifestyle

Need or Demand:

In my first voice lesson at NYU I was told that the sound of my voice was like cheese being grated.  This sound is not unique, it has a name, and it is a destructive speech pattern prevalent among young women (in their 20s and 30s) in the US, the UK and Australia. It is called “vocal fry” and it’s a result of a lower subglottic pressure constricting airflow through the voice box and in doing so produces a grating, gravely, and creaky growl at the back of the throat.  Think valley girl talk, Kim Kardashian, or whatever you can imagine for the speech pattern of a “ditzy” young woman.  A study, published in the journal PLOS ONE says,“Relative to a normal speaking voice, young adult female voices exhibiting vocal fry are perceived as less competent, less educated, less trustworthy, less attractive, and less hirable.” We live in an exciting time with

more women role models than ever; however, vocal fry is a significant obstacle to the progress of gender equality.  The problem is that treating vocal fry is an expensive (~$100/ session), inaccessible and lengthy process that’s almost impossible to do on your own. Therefore, there exists a clear need for a vocal analytics

Product / Service / Solution:

Although vocal fry is easily detected by the listener, it can be very difficult to detect on your own, as well as understand how to get rid of it. In order to provide accessible vocal therapy, I will create an mobile app that utilizes algorithms to analyze the users’ speech patterns to detect vocal fry. This will be paired with vocal coaching videos that serve as a tool to correct users’ speech. Specifically, each exercise will be accessible in an order that resembles a typical vocal coaching session.  After the user plays the training video exercise they will be prompted to voice it over.  When they are finished, the sound waves of their session will be displayed in a side-by-side comparison. In each successive interval that the algorithm detects vocal fry, the user will be able to play back their speech and then compare it to the associated training video interval. This comparison will help detect vocal fry and enable the user to correct it. In order to advance to the next exercise, they must complete the previous one with vocal precision. As users progress through the exercises they will cultivate an understanding of their voice. In particular, they will learn how to produce a more even and efficient quality of sound.

Value Proposition:

This mobile app provides my customer segment, young women in the US, the UK and Australia, with easily accessible and inexpensive vocal training. By using my app to improve voice and speech, my users will be better equipped to succeed in social and workplace settings by eliminating voice-related insecurity and anxiety.

For ordinary women, the app can function as a stand-alone service to improve their voice and thus outside social perception. For artists and performers, on the other hand, it can complement professional vocal coaching with structured and data-driven practice.

Competition:

The primary competition is Vocular – an mobile app that analyzes users’ vocal depth and variance and compares with celebrities to give them an idea of how “attractive” they sound.  Given the color scheme and emphasis on voice deepening, Vocular appears to be marketed to men. They do, however, detect a users’ percentage of vocal fry but fail to provide in-app techniques to solve this issue.

Additionally, the app’s usage has revealed glaring flaws:

1)  The poor UI (the app is seemingly built with a web framework like Electron) is unintuitive and confusing.

2)  The app crashes when a recording eclipses just 20 seconds.

3)  The app’s algorithm matched my voice with Emma Watson and Queen Elizabeth while I have an American accent.

4)  Vocal fry detection is given as a percentage over the range of time speaking into the recorder providing metrics without personal insights.

Unlike Vocular, Fryyed will be a mobile-first app that helps my target audience with real-time voice analytics and comprehensive vocal coaching. My goal is to help young women eliminate voice-related insecurities and anxieties without gimmicky celebrity comparisons. In the end, Vocular is barely a competitor to Fryyed.

Revenue Model:

The app will be free to download and will provide a core freemium model with a vocal range breakdown feature. Premium features like vocal fry detection, voice data analytics and instructional videos will be accessible through a subscription of $6.99/month or $59.99/year per user. However, before we reach a critical mass of users, the premium features will be free.