Skip to content

Github Repository for the work done as a part of term project in the Machine Learning Course 2016.

Notifications You must be signed in to change notification settings

cs60050/TeamRocket

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

20 Commits
 
 
 
 
 
 

Repository files navigation

Song Lyrics Generation

TeamRocket

Machine Learning Project

Abstract

Writing lyrics require creativity to construct a meaningful, and interesting story and capture the mood of the music listeners. Every band/artist has a unique style and this could be abstracted out using Machine Learning tools. We generated the song word by word and used LSTM to predict which word should come next from the current word and current context which is captured very well by the LSTM model. This helped us to generate the initial lyrics. Further the so generated lyrics, was given to a set of users which was interpreted in a very similar fashion, which shows that the basic essence and vibe of the band was effectively captured by using LSTM. Evaluation metrics were borderline essentric. We had to decide and toy around with Rhythm density, and tf-idf measures.

Members

  • R. Naresh
  • Himanshu Verma
  • Prateek Jhunjhunwala
  • Harsh Bajoria
  • Rahul Sonanis
  • Sandeep Pani
  • Shubham Jain
  • Ankur Garg
  • Sayan Mukhopadhyay
  • Vishwas Jain
  • Abhinav Sharma
  • Satyarth Singh

About

Github Repository for the work done as a part of term project in the Machine Learning Course 2016.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 3

  •  
  •  
  •  

Languages