We investigated methods for the discovery of clichés from song lyrics. Trigrams and rhyme features were extracted from a collection of lyrics and ranked using term-weighting techniques such as tf-idf. These attributes were also examined over both time and genre. We present an application to produce a cliché score for lyrics based on these findings and show that number one hits are substantially...

Deep cross-modal learning has successfully demonstrated excellent performances in cross-modal multimedia retrieval, with the aim of learning joint representations between different data modalities. Unfortunately, little research focuses on cross-modal correlation learning where temporal structures of different data modalities such as audio and lyrics are taken into account. Stemming from the ch...

Multimedia data by definition comprises several different types of content modalities. Music specifically inherits e.g. audio at its core, text in the form of lyrics, images by means of album covers, or video in the form of music videos. Yet, in many Music Information Retrieval applications, only the audio content is utilised. Recent studies have shown the usefulness of incorporating other moda...

Computational creativity is one area of NLP which requires extensive analysis of large datasets. Laalalaa [1] framework for Lyric analysis and generation proposed a lyric analysis subsystem that required statistical analysis of Tamil lyrics. In this paper, we propose a data analysis model for words, rhymes and their usage in Tamil lyrics. The proposed analysis model extracts the root words from...

Recently, several music information retrieval (MIR) systems which retrieve musical pieces by the user’s singing voice have been developed. All of these systems use only melody information for retrieval, although lyrics information is also useful for retrieval. In this paper, we propose a new MIR system that uses both lyrics and melody information. First, we propose a new lyrics recognition meth...

This paper proposes an improved query by singing/humming (QBSH) system using both melody and lyrics information for achieving better performance. Singing/humming discrimination (SHD) is first performed to distinguish singing from humming queries. For a humming query, we apply a pitch-only melody recognition method that has been used for QBSH task at MIREX with rank-1 performance. For a singing ...

Songs naturally bind lyrics and melody into a unified representation. Using a subsequent memory paradigm, we examined the neural processes associated with binding lyrics and melodies during song encoding. Participants were presented with songs in two conditions: a unified condition (melodies sung with lyrics), and a separate condition (melodies sung with the syllable "la"). In both cases, writt...

Imperfect and internal rhymes are two important features in rap music often ignored in the music information retrieval community. We develop a method of scoring potential rhymes using a probabilistic model based on phoneme frequencies in rap lyrics. We use this scoring scheme to automatically identify internal and line-final rhymes in song lyrics and demonstrate the performance of this method c...

When analyzing singing voice signal, it is required to know the boundaries of each phonetic unit in the singing voice samples. However, due to prolonged vowels in the singing voice, it is not easy to accurately align a singing voice with the phonetic sequence of its lyrics by conventional speech recognition approach. This paper proposes a solution for the phonetic annotation of the singing voic...

This paper is about an ongoing project, Tra-la-Lyrics which aims to create a computer program capable of generating lyrics for given melodies. As a preliminary phase, the correlations between words and rhythm in a song’s lyrics was studied and some heuristics were achieved. Algorithms for syllabic division and syllabic stress identification on a word were implemented. A method for calculating t...