Show simple item record

dc.contributor.authorSinghi, Abhishek 18:26:56 (GMT) 18:26:56 (GMT)
dc.description.abstractMusic Information Retrieval (MIR) research tends to focus on audio features like melody and timbre of songs while largely ignoring lyrics. Lyrics and poetry adhere to a specific rhyme and meter structure which set them apart from prose. This structure could be exploited to obtain useful information, which can be used to solve Music Information Retrieval tasks. In this thesis we show the usefulness of lyrics in solving MIR tasks. For our first result, we show that the presence of lyrics has a variety of significant effects on how people perceive songs, though it is unable to significantly increase the agreement between Canadian and Chinese listeners about the mood of the song. We find that the mood assigned to a song is dependent on whether people listen to it, read the lyrics or both together. Our results suggests that music mood is so dependent on cultural and experiental context to make it difficult to claim it as a true concept. We also show that we can predict the genre of a document based on the adjective choices made by the authors. Using this approach, we show that adjectives more likely to be used in lyrics are more rhymable than those more likely to be used in poetry and are also able to successfully separate poetic lyricists like Bob Dylan from non-poetic lyricists like Bryan Adams. We then proceed to develop a hit song detection model using 31 rhyme, meter and syllable features and commonly used Machine Learning algorithms (Bayesian Network and SVM). We find that our lyrics features outperform audio features at separating hits and flops. Using the same features we can also detect songs which are likely to be shazamed heavily. Since most of the Shazam Hall of Fame songs are by upcoming artists, our advice to them is to write lyrically complicated songs with lots of complicated rhymes in order to rise above the "sonic wallpaper", get noticed and shazamed, and become famous. We argue that complex rhyme and meter is a detectable property of lyrics that indicates quality songmaking and artisanship and allows artists to become successful.en
dc.publisherUniversity of Waterloo
dc.subjectMusic Information Retrievalen
dc.subjectMachine Learningen
dc.titleLyrics Matter: Using Lyrics to Solve Music Information Retrieval Tasksen
dc.typeMaster Thesisen
dc.subject.programComputer Scienceen Science (David R. Cheriton School of)en
uws-etd.degreeMaster of Mathematicsen

Files in this item


This item appears in the following Collection(s)

Show simple item record


University of Waterloo Library
200 University Avenue West
Waterloo, Ontario, Canada N2L 3G1
519 888 4883

All items in UWSpace are protected by copyright, with all rights reserved.

DSpace software

Service outages