Singing voice is specific in music: a vocal performance conveys both music (melody/pitch) and lyrics (text/phoneme) content. This paper aims at exploiting the advantages of melody and lyric information for real-time audio-to-score alignment of singing voice. First, lyrics are added as a separate observation stream into a template-based hidden semi-Markov model (HSMM), whose observation model is...

Research shows that sensational news stories as well as popular romance novels often feature themes related to important topics in evolutionary psychology. In the first of four studies described in this paper we examined the song lyrics from three Billboard charts: Country, Pop, and R&B. A content analysis of the lyrics revealed 18 reproductive themes that read like an outline for a course in e...

Music is an ever-changing cultural reflection. It is deeply integrated into our society, ubiquitous in movies, television shows, restaurants, sport venues, churches and a plethora of other places. This thesis proposes that we consider the lyrics in popular music, as determined by Billboards Hot 100 chart, as a natural medium to analyze the changes in culture over the past half-century. Using th...

Optical music recognition (OMR) is one of the most promising tools for generating large-scale, distributable libraries of musical data. Much OMR work has focussed on instrumental music, avoiding a special challenge vocal music poses for OMR: lyric recognition. Lyrics complicate the page layout, making it more difficult to identify the regions of the page that carry musical notation. Furthermore...

This paper describes a singing-to-speaking synthesis system called “SpeakBySinging” that can synthesize a speaking voice from an input singing voice and the song lyrics. The system controls three acoustic features that determine the difference between speaking and singing voices: the fundamental frequency (F0), phoneme duration, and power (volume). By changing these features of a singing voice,...

Melody generation from lyrics has been a challenging research issue in the field of artificial intelligence and music, which enables to learn discover latent relationship between interesting accompanying melody. Unfortunately, limited availability paired lyrics-melody dataset with alignment information hindered progress. To address this problem, we create large consisting 12,197 MIDI songs each...

This paper presents a novel task, namely the automatic identification of ageappropriate ratings of a musical track, or album, based on its lyrics. Details are provided regarding the construction of a dataset of lyrics from 12,242 tracks across 1,798 albums along with age-appropriate ratings obtained from various web resources, along with results from various text classification experiments. The...

Solving the task of phoneme recognition in music sound files may help for several practical applications: it enables lyrics transcription and as a consequence could provide further relevant information for the task of an automatic song classification. Beyond it can be used for lyrics alignment e.g. in karaoke applications. The effect of both different feature signal representations as well as t...

We cast the problem of hip hop lyric generation as a translation problem, automatically learn a machine translation system that accepts hip hop lyric challenges and improvises rhyming responses, and show that improving the training data by learning an unsupervised rhyme detection scheme further improves performance. Our approach using unsupervised induction of stochastic transduction grammars i...

We attack a woefully under-explored language genre—lyrics in music—introducing a novel hidden Markov model based method for completely unsupervised identifica-tion of rhyme schemes in hip hop lyrics, which to the best of our knowledge, is the first such effort. Unlike previous approaches that use supervised or semi-supervised approaches for the task of rhyme scheme identification, our model doe...